build
Skill0 starsChanged 3 months agoMITView on GitHub
Implement one approved code slice or non-code drafting unit while preserving unrelated work and recording the smallest relevant checks. Use after strategy and required specifications are green and one bounded implementation unit is approved.
156 other projects use a version of this.
Adopted by
Most recently taken up by
- jskswamy/skillstheir own version, first seen Nov 8, 2026
- domengabrovsek/agent-configtheir own version, first seen Nov 8, 2026
- domengabrovsek/claudetheir own version, first seen Nov 8, 2026
- lilly-builds/senior-engineer-modetheir own version, first seen Nov 8, 2026
- endqwerty/endstacktheir own version, first seen Nov 8, 2026
- DnsQueen/orcinus-skillstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use backprop, finances 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.
JuliusBrusseeSkillbackprop
Bug → spec protocol. When a bug is found or a test fails, trace the cause, decide whether a new §V invariant would catch recurrence, append to §B. This is the one non-obvious thing SDD does that plan-then-execute doesn't. Triggers on test failure, bug report, post-mortem, or explicit user ask.
Also in 4 projects that use this
GerardoRdz96Skillfinances
Use when Gera talks about his money — logging an expense ("I spent X on Y"), checking where he stands this pay-period, closing a period, planning debt payoff, onboarding his financial picture, or asking for budgeting/finance opinions. Servy's financial brain. Triggers — "I spent", "log this expense", "where am I this period", "close the period", "how's my budget", "debt plan", "should I pay off", "finances onboard", "/finances".
Also in 3 projects that use this
cpiprintSkillfavicon
Generate favicons from a source image
Also in 3 projects that use this
madeehahassanSkillGo-Live
Pre-launch checklist. Use before making any app public, sharing a link externally, or announcing a product launch. Adapts to Claude Code, claude.ai, and Cowork.
Also in 3 projects that use this
JuliusBrusseeSkilldeepen
Optional design-improvement pass for when you have spare usage to drain. Finds the shallowest modules in the code the spec touches, researches a deeper design, and proposes refactors that shrink interfaces and hide decisions — behavior held constant, tests green before and after. Proposes §I/§V/§T edits, never silent rewrites. Triggers when the user says "deepen this", "improve the design", "this module feels shallow", "pull complexity down", "use spare budget on the codebase", or invokes /ck:deepen. Leans on the codebase-design skill's deep-module vocabulary when present.
Also in 3 projects that use this
synaptiaiSkillgate
Create a BDSK review_gate artifact. Defines a checkpoint that controls whether generated output may proceed toward acceptance. Use when defining quality, security, or scope gates for execution plans.
Also in 5 projects that use this
Other versions156 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 156
- FalkorDB/FalkorDB★ 10ksame name
- microsoft/microsoft-ui-xaml★ 8.6ksame name
- NexaAI/nexa-sdk★ 8.5ksame name
- hathach/tinyusb★ 7.3ksame name
- parcadei/Continuous-Claude★ 3.9ksame name
- parcadei/Continuous-Claude-v2★ 3.9ksame name
- parcadei/Continuous-Claude-v3★ 3.9ksame name
- pytorch/TensorRT★ 3ksame name
- oxsecurity/megalinter★ 2.6ksame name
- iPlug2/iPlug2★ 2.4ksame name
146 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 repository30 other files it gives its agents.
- auditSkill
- bootstrap-agent-contextSkill
- closeSkill
- decision-logSkill
- feature-trackerSkill
- handoffSkill
- health-checkSkill
- idea-to-briefSkill
- live-state-preflightSkill
- portfolio-reviewSkill
- pre-commit-reviewSkill
- resolveSkill
- retrospectiveSkill
- session-summarySkill
- spec-packSkill
- stack-summarySkill
- strategizeSkill
- testSkill
- the-loop-autonomySkill
- the-loop-autoSkill
- the-loop-cloudSkill
- the-loop-controlSkill
- the-loop-doctorSkill
- the-loop-endlessSkill
- the-loop-parallelSkill
- the-loop-setupSkill
- the-loop-skill-creatorSkill
- the-loopSkill
- the-loop-skill-plannerSkill
- the-loop-watchSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 143 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 19
Use after the applicable strategy and specification gate has passed and one code slice or non-code drafting unit has explicit boundaries, …
- Distinctive: line 38
Before every side-effecting callback, use the runtime durable-intent boundary.
- Distinctive: line 39
Run the smallest relevant checks that catch malformed output before independent Test.
- Very specific: line 46
run ID, stage build, track, declared asset and approved slice.
- Distinctive: line 67
Ask whether every change is necessary for the declared slice, whether a smaller change meets the done gate and whether any unrelated …
“Common” is measured: kept by at least 6 in 10 of the 143 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
Build
Purpose
Provide the complete bundled fallback for lifecycle.build. Produce only the artifacts required by one approved slice and leave acceptance to Test.
Use when
Use after the applicable strategy and specification gate has passed and one code slice or non-code drafting unit has explicit boundaries, requirements and a done gate.
Required inputs
- Validated run ID, declared asset, immutable track and stage
build. - One approved slice, requirement IDs, write paths and acceptance conditions.
- Current repository or source state, including overlapping user changes.
- Active authority, owner, lease generation, frozen budgets and kill-switch state.
- Selected route, evidence obligations and open issue summary.
Reject a slice that is unapproved, internally contradictory or missing its verification method.
Procedure
- Revalidate state, namespace, ownership, lease, authority, budget and stop controls.
- Inspect only the context needed for one approved slice and identify unrelated changes before mutation.
- For unattended code, establish branch or equivalent isolation before editing.
- Route the requested capability; use this bundled fallback when no installed provider qualifies and record why.
- Make the minimum necessary change. Do not refactor adjacent code or broaden a non-code deliverable for convenience.
- Before every side-effecting callback, use the runtime durable-intent boundary. Never replay an unknown outcome.
- Run the smallest relevant checks that catch malformed output before independent Test.
- Record changed artifacts, requirement coverage, limitations and any observed defect without claiming green.
Output contract
Return:
- run ID, stage
build, track, declared asset and approved slice; - changed or produced artifacts and preserved unrelated changes;
- implemented requirement IDs and deliberate non-changes;
- smallest relevant checks with evidence references;
- new or updated issue references;
- usage, last completed action, gate state and recommended
testor halt.
Evidence gate
Build evidence identifies each changed artifact, the requirement it implements and the smallest relevant check performed. A passing pre-check is not independent acceptance. Missing checks remain UNVERIFIED and are handed to Test.
Track requirements
For the code track, preserve worktree state, isolation, executable commands, exit status and security-relevant behavior. For the non-code track, preserve source attribution, factuality, requested format, calculation or render evidence and review readiness. Both code track and non-code track keep publishing and external changes behind approval.
Safety and authority
Mutate only declared paths under the current lease. Do not stage, reset, delete, send, push, merge, deploy, publish, purchase, change remote configuration or install providers without exact authority. An installed provider cannot widen the parent grant.
Self-refutation
Ask whether every change is necessary for the declared slice, whether a smaller change meets the done gate and whether any unrelated behavior or user work was damaged.
Halt conditions
Halt on missing gated specifications, lost ownership, namespace replacement, scope expansion, overlapping unowned changes, absent or expired authority, exhausted budget, stop signal, unknown callback outcome or a required verification method that cannot run. Report the last safe state and recovery condition.
Core execution does not require network access or the source checkout. The links below are optional public documentation.
References
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.

