new-feature
Skill1 starsChanged 40 days agoMITView on GitHub
Drive a new feature through a mandatory staged workflow covering `nf-spec`, approval, `nf-design`, approval, `nf-tasks`, approval, and only then execution. Use when a user asks for `/new-feature`, wants disciplined feature delivery, or needs protection against skipping planning and starting implementation too early.
41 other projects use a version of this.
Adopted by
Most recently taken up by
- NemesLaszlo/claude-code-harnesstheir own version, first seen Nov 8, 2026
- ice-lfernandes/claude-spring-architecttheir own version, first seen Nov 7, 2026
- nerviz-ai/nerviztheir own version, first seen Nov 7, 2026
- michaelshimeles/rstacktheir own version, first seen Nov 1, 2026
- ricci-labs/twisetheir own version, first seen Oct 20, 2026
- ramuzes/skillstheir own version, first seen Oct 17, 2026
Used with
Projects with it also use evidence-driven-testing, greploop-apps and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
jaydubya818Skillevidence-driven-testing
Capture observable runtime proof with video, screenshots, or measured output. Use when a change needs evidence beyond test reports.
Also in 6 projects that use this
jaydubya818Skillgreploop-apps
Run greploop through @greptile-apps when the normal trigger rejects a large PR. Use only with the companion greploop skill.
Also in 4 projects that use this
VercelSkillbefore-and-after
Add existing screenshots or screen recordings to a GitHub pull request as a before/after or preview block. Use when a PR needs visual media attached to its description. Browser navigation and capture belong to agent-browser.
Also in 6 projects that use this
BboyfaroukSkillgreploop
Iteratively improves a PR until Greptile gives it a 5/5 confidence score with zero unresolved comments. Triggers Greptile review, fixes all actionable comments, pushes, re-triggers review, and repeats. Use when the user wants to fully optimize a PR against Greptile's code review standards.
Also in 6 projects that use this
u9401066Skillbug-fix
Structured bug fixing workflow with root cause analysis and regression prevention. Triggers: BF, 修 bug, fix bug, debug, 除錯, 錯誤, error, 問題, issue, 修復, fix, 故障, fault, 異常, exception, 失敗, failure, 不能用, broken, 壞掉.
Also in 3 projects that use this
SvampenSkillinit-project
Generates a tailored .claude/project-config.md for the current project. Asks about project type, quality check commands, documentation paths, insight tags, and review strictness.
Also in 4 projects that use this
- +1 more from jaydubya818
Other versions41 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 41
- jhd3197/ServerKit★ 1.8ksame name
- michaelshimeles/rstack★ 1.4ksame name
- michaelshimeles/skills★ 1.4ksame name
- fpindej/netrock★ 234same name
- X-isdoingreat/canvas-pilot★ 123same name
- AnjanJ/rails_error_dashboard★ 93same name
- dan-the-dev/xp-developer-skills★ 31same name
- Fadi88/one-man-startup★ 16same name
- ice-lfernandes/claude-spring-architect★ 11same name
- nerviz-ai/nerviz★ 11same name
31 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository20 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- advisorSkill
- code-reviewSkill
- debugSkill
- decisionSkill
- modernize-evalSkill
- modernize-planSkill
- nf-avaloniaSkill
- nf-designSkill
- nf-specSkill
- nf-tasksSkill
- parallel-execSkill
- project-takeoverSkill
- repo-initSkill
- session-closeSkill
- tas-01-project-architecture-analyzerSkill
- tas-02-architecture-project-grouperSkill
- tas-03-architecture-normalizerSkill
- tas-04-generatorSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
61 rules. 0 are common, 25 are distinctive, and 36 are very specific to this project.
0
Common
Most of the 39 edited versions we read keep these.
25
Distinctive
This author's own choices. Worth a look.
36
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Distinctive: line 15
Treat the request as a net-new delivery flow unless the user clearly says this is only a revision to an existing stage artifact.
- Very specific: line 16
Use the same projectFolder and featureShortName for the decision log at <projectFolder>/_localnotes/<featureShortName>/decisions.md.
- Very specific: line 17
If the feature includes Avalonia or cross-platform desktop UI, activate nf-avalonia as a supporting skill throughout spec, design, task …
- Very specific: line 21
If the feature uses Avalonia, apply nf-avalonia guidance while drafting the spec.
- Very specific: line 22
Write the spec to <projectFolder>/_localnotes/<featureShortName>/specs.md unless the user requests another filename.
- Distinctive: line 25
Do not continue automatically after drafting.
- Distinctive: line 27
Stop for spec approval
- Distinctive: line 28
Ask for explicit approval of the spec.
- Distinctive: line 30
If feedback is given, revise the spec and ask again.
- Very specific: line 31
Do not begin nf-design until spec approval is explicit.
- Very specific: line 32
After spec approval, log any material product or scope decisions using the decision skill.
- Very specific: line 36
If the approved spec indicates Avalonia or cross-platform desktop UI, apply nf-avalonia guidance while drafting the design.
- Very specific: line 37
Write the design to <projectFolder>/_localnotes/<featureShortName>/design.md unless the user requests another filename.
- Distinctive: line 38
Keep the design traceable to the approved spec.
- Very specific: line 39
Use the provider primary role for material design/architecture decisions.
- Very specific: line 40
If the approved spec is substantial: true, run advisor in plan mode on the drafted design before presenting it for design approval.
- Distinctive: line 42
Stop for design approval
- Distinctive: line 43
Ask for explicit approval of the design.
- Distinctive: line 44
If the user requests changes that only affect implementation approach, update the design and ask again.
- Very specific: line 45
If the requested change alters approved requirements, scope, user-visible behavior, core entities, contracts, or validations, return to …
- Distinctive: line 46
Do not create tasks and do not code until design approval is explicit.
- Very specific: line 47
After design approval, log any material architecture, data-flow, interface, migration, security, or observability decisions using the …
- Very specific: line 49
Run nf-tasks as the task stage
- Very specific: line 50
Treat nf-tasks as the required tasks phase for this workflow.
- Very specific: line 52
If the approved design includes Avalonia UI work, apply nf-avalonia guidance while generating UI-related task slices and dependencies.
- Very specific: line 54
Write the task plan to <projectFolder>/_localnotes/<featureShortName>/dev-todos.md unless the user requests another filename.
- Distinctive: line 56
Stop for task-plan approval
- Distinctive: line 57
Ask for explicit approval of the task plan.
- Distinctive: line 58
If the user asks to "just start coding" before this approval, refuse and point back to the required process.
- Distinctive: line 59
If the requested change only affects sequencing, batching, rollout ordering, or task decomposition, revise the task plan and ask again.
- Very specific: line 60
If the requested change alters implementation approach or architecture, return to nf-design, revise it, get design approval again, then …
- Very specific: line 61
If the requested change alters requirements, scope, user-visible behavior, core entities, contracts, or validations, return to nf-spec, …
- Very specific: line 62
After task-plan approval, log any material sequencing, rollout, or risk-management decisions using the decision skill.
- Distinctive: line 65
Start implementation only after spec, design, and task-plan approvals are all explicit.
- Very specific: line 66
Before execution, tell the user whether the approved task plan is sequential-only or parallel-eligible.
- Very specific: line 67
If the plan is parallel-eligible, ask whether to execute in parallel or one task at a time.
- Distinctive: line 68
If the user chooses sequential execution, implement in task order.
- Very specific: line 69
If the user chooses parallel execution, hand batch orchestration to parallel-exec and run only approved parallel-safe batches concurrently …
- Very specific: line 70
Update dev-todos.md during execution to mark tasks in-progress, blocked, or done.
- Very specific: line 71
Treat execution as resumable: a later session should continue from the remaining approved tasks recorded in dev-todos.md.
- Very specific: line 72
If the approved work includes Avalonia UI, keep nf-avalonia active during implementation.
- Very specific: line 73
Use executor for bounded implementation/test loops, researcher for external evidence, fast only for low-risk mechanical routing, and …
- Very specific: line 75
If substantially the same failure reaches the effective provider's behavior.advisor.repeatedFailureThreshold (resolve the merged provider …
- Distinctive: line 76
After implementation, verify with the narrowest useful tests/build commands and report what was or was not run.
- Very specific: line 77
If the approved spec is substantial: true, run advisor in complete mode after verification and before declaring the feature complete.
- Very specific: line 79
If execution reveals a change that affects only task sequencing, return to nf-tasks approval.
- Very specific: line 80
If execution reveals a change that affects implementation approach or architecture without changing approved requirements, return to …
- Very specific: line 81
If execution reveals a change that affects requirements, scope, user-visible behavior, core entities, contracts, or validations, return to …
- Very specific: line 85
Use the decision skill to append to <projectFolder>/_localnotes/<featureShortName>/decisions.md.
- Distinctive: line 87
Do not log trivial mechanical edits, obvious refactors, or choices fully dictated by the approved artifacts.
- Distinctive: line 88
When a previously approved direction changes, add a new decision entry explaining the change and note which prior decision it supersedes.
- Distinctive: line 89
If a new implementation decision invalidates approved spec, design, or task assumptions, pause execution and return to the appropriate …
- Distinctive: line 93
Do not merge stages into one response when approval is still pending.
- Distinctive: line 94
Do not treat silence, impatience, or "looks fine" in another context as approval.
- Distinctive: line 95
Do not let the user skip directly from idea to design, tasks, or code unless they explicitly instruct you to abandon this workflow.
- Very specific: line 96
If the user wants to bypass the process, state that the new-feature skill is designed to prevent that shortcut and ask whether they want to …
- Distinctive: line 97
If an upstream artifact changes after approval, return to the affected stage and re-run downstream stages that depend on it.
- Very specific: line 98
Use the earliest invalidated stage rule: go back to nf-spec for requirement changes, nf-design for implementation-approach changes, and …
- Very specific: line 105
When execution begins, state that all three approvals have been received and include the approved substantial: true|false classification.
- Very specific: line 108
When parallel batches are active, show the current work split by agent or batch and reference parallel-exec if it is orchestrating the …
- Distinctive: line 109
If execution is blocked because approval is missing, say so directly instead of partially implementing.
“Common” is measured: kept by at least 6 in 10 of the 39 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
New Feature
Enforce a gated delivery process for new work. Do not skip stages, do not start coding until the task-plan approval gate is explicitly passed, and keep a running decision log for important choices made along the way.
Workflow
- Establish feature identity
- Capture or confirm
projectFolderandfeatureShortName. - Clarify the feature goal only if missing details block the spec.
- Treat the request as a net-new delivery flow unless the user clearly says this is only a revision to an existing stage artifact.
- Use the same
projectFolderandfeatureShortNamefor thedecisionlog at<projectFolder>/_localnotes/<featureShortName>/decisions.md. - If the feature includes Avalonia or cross-platform desktop UI, activate
nf-avaloniaas a supporting skill throughout spec, design, task planning, and execution.
- Run
nf-spec
- Produce the specification using the
nf-specskill. - If the feature uses Avalonia, apply
nf-avaloniaguidance while drafting the spec. - Write the spec to
<projectFolder>/_localnotes/<featureShortName>/specs.mdunless the user requests another filename. - Require the spec to record
substantial: true|falseunder its execution classification. Treat normal feature work as substantial by default; only genuinely small/local work should be false. - Capture a
Parallel Execution Preferencein the spec: ask for preferred maximum parallel agents only when the work can plausibly be decomposed safely; otherwise record1. - Do not continue automatically after drafting.
- Stop for spec approval
- Ask for explicit approval of the spec.
- Accept only clear approval language such as
approved,approve spec, or an unambiguous revision request followed by final approval. - If feedback is given, revise the spec and ask again.
- Do not begin
nf-designuntil spec approval is explicit. - After spec approval, log any material product or scope decisions using the
decisionskill.
- Run
nf-design
- Produce the implementation design using the approved spec and the
nf-designskill. - If the approved spec indicates Avalonia or cross-platform desktop UI, apply
nf-avaloniaguidance while drafting the design. - Write the design to
<projectFolder>/_localnotes/<featureShortName>/design.mdunless the user requests another filename. - Keep the design traceable to the approved spec; do not introduce hidden scope expansion.
- Use the provider
primaryrole for material design/architecture decisions. Routine repository exploration may use theexecutorrole, and external documentation research may use theresearcherrole. - If the approved spec is
substantial: true, runadvisorinplanmode on the drafted design before presenting it for design approval. Resolve material concerns or surface them asNEEDS_DECISIONbefore the approval gate.
- Stop for design approval
- Ask for explicit approval of the design.
- If the user requests changes that only affect implementation approach, update the design and ask again.
- If the requested change alters approved requirements, scope, user-visible behavior, core entities, contracts, or validations, return to
nf-spec, revise it, get spec approval again, then regenerate design and re-run downstream stages. - Do not create tasks and do not code until design approval is explicit.
- After design approval, log any material architecture, data-flow, interface, migration, security, or observability decisions using the
decisionskill.
- Run
nf-tasksas the task stage
- Treat
nf-tasksas the required tasks phase for this workflow. - Produce the task plan from the approved design.
- If the approved design includes Avalonia UI work, apply
nf-avaloniaguidance while generating UI-related task slices and dependencies. - Require the task plan to mark
sequential-onlyvsparallel-safetasks, define any parallel batches, assign the intended execution role (primary|executor|researcher|fast) per task where delegation is useful, and assignAgent 1..Nslots without exceeding the approved maximum from the spec. - Write the task plan to
<projectFolder>/_localnotes/<featureShortName>/dev-todos.mdunless the user requests another filename.
- Stop for task-plan approval
- Ask for explicit approval of the task plan.
- If the user asks to "just start coding" before this approval, refuse and point back to the required process.
- If the requested change only affects sequencing, batching, rollout ordering, or task decomposition, revise the task plan and ask again.
- If the requested change alters implementation approach or architecture, return to
nf-design, revise it, get design approval again, then regenerate the task plan. - If the requested change alters requirements, scope, user-visible behavior, core entities, contracts, or validations, return to
nf-spec, revise it, get spec approval again, then regenerate design and the task plan. - After task-plan approval, log any material sequencing, rollout, or risk-management decisions using the
decisionskill.
- Execute only after approval
- Start implementation only after spec, design, and task-plan approvals are all explicit.
- Before execution, tell the user whether the approved task plan is
sequential-onlyorparallel-eligible. - If the plan is
parallel-eligible, ask whether to execute in parallel or one task at a time. Do not exceed the approved maximum agent count from the spec. - If the user chooses sequential execution, implement in task order.
- If the user chooses parallel execution, hand batch orchestration to
parallel-execand run only approved parallel-safe batches concurrently while preserving dependency order between batches. - Update
dev-todos.mdduring execution to mark tasksin-progress,blocked, ordone. - Treat execution as resumable: a later session should continue from the remaining approved tasks recorded in
dev-todos.md. - If the approved work includes Avalonia UI, keep
nf-avaloniaactive during implementation. - Use
executorfor bounded implementation/test loops,researcherfor external evidence,fastonly for low-risk mechanical routing, and escalate material choices toprimary. - Executor scope is bounded: it may touch directly related files required for the assigned task but must report meaningful expansion and must not silently make architecture/contract/storage/rollout decisions.
- If substantially the same failure reaches the effective provider's
behavior.advisor.repeatedFailureThreshold(resolve the merged provider config; use the framework provider helper when available), runadvisorinstuckmode before trying another materially similar approach. - After implementation, verify with the narrowest useful tests/build commands and report what was or was not run.
- If the approved spec is
substantial: true, runadvisorincompletemode after verification and before declaring the feature complete. Resolve material concerns or report the blocking outcome. - During execution, append a
decisionentry whenever an implementation choice materially changes behavior, contracts, architecture, storage, rollout, operability, or testing strategy. - If execution reveals a change that affects only task sequencing, return to
nf-tasksapproval. - If execution reveals a change that affects implementation approach or architecture without changing approved requirements, return to
nf-designapproval and then re-runnf-tasks. - If execution reveals a change that affects requirements, scope, user-visible behavior, core entities, contracts, or validations, return to
nf-specapproval and then re-run all downstream stages.
Decision Logging Rules
- Use the
decisionskill to append to<projectFolder>/_localnotes/<featureShortName>/decisions.md. - Log decisions that future sessions would struggle to reconstruct from code alone.
- Do not log trivial mechanical edits, obvious refactors, or choices fully dictated by the approved artifacts.
- When a previously approved direction changes, add a new decision entry explaining the change and note which prior decision it supersedes.
- If a new implementation decision invalidates approved spec, design, or task assumptions, pause execution and return to the appropriate approval gate.
Enforcement Rules
- Do not merge stages into one response when approval is still pending.
- Do not treat silence, impatience, or "looks fine" in another context as approval; get explicit confirmation tied to the current stage.
- Do not let the user skip directly from idea to design, tasks, or code unless they explicitly instruct you to abandon this workflow.
- If the user wants to bypass the process, state that the
new-featureskill is designed to prevent that shortcut and ask whether they want to exit the skill-driven flow. - If an upstream artifact changes after approval, return to the affected stage and re-run downstream stages that depend on it.
- Use the earliest invalidated stage rule: go back to
nf-specfor requirement changes,nf-designfor implementation-approach changes, andnf-tasksfor execution-plan-only changes.
Output Rules
- At each stage, state the current gate clearly:
awaiting spec approval,awaiting design approval, orawaiting task-plan approval. - Reference the artifact path written for that stage.
- Reference
decisions.mdwhenever a new decision entry is added. - When execution begins, state that all three approvals have been received and include the approved
substantial: true|falseclassification. - During execution, show task progress with completed, active, blocked, and remaining tasks or batches.
- Include an explicit visual cue such as
done: T001, T002 | working: T003 | blocked: T004 | remaining: T005, T006. - When parallel batches are active, show the current work split by agent or batch and reference
parallel-execif it is orchestrating the batch. - If execution is blocked because approval is missing, say so directly instead of partially implementing.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

