task-planning
Skill0 starsChanged 3 months agoMITView on GitHub
Turn a ready plan or plain task description into a validated, repository-aware TASK_PLAN.md. Detects existing/related features, verifies paths, plans normal tasks and complete projects, and prevents silent scope expansion.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- NoobyGains/godmodetheir own version, first seen Nov 1, 2026
- microsoft/amplifier-app-papercliptheir own version, first seen Oct 25, 2026
- LOUSANPANG/agent-skillstheir own version, first seen Sep 2, 2026
- lasp/adamant-skillstheir own version, first seen Aug 13, 2026
- TTflysky/sirenhuisuotheir own version, first seen Aug 4, 2026
- 5kuper/ai-docs-kittheir own version, first seen May 25, 2026
Used with
Projects with it also use code-review.
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.
GoogleSkillcode-review
Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.
Also in 3 projects that use this
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- NoobyGains/godmode★ 118same name
- lasp/adamant-skills★ 4same name
- TTflysky/sirenhuisuo★ 4same name
- zebbern/termstack★ 4same name
- LOUSANPANG/agent-skills★ 2same name
- microsoft/amplifier-app-paperclip★ 1same name
- youjun011/skills★ 1same name
- 5kuper/ai-docs-kit★ 0same name
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 repository8 other files it gives its agents.
- codex-reviewSkill
- deploymentSkill
- feature-changelogSkill
- frappe-taskSkill
- git-finalizationSkill
- project-contextSkill
- task-implementationSkill
- testing-taskSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 50
Every implementation step must be specific and verifiable (template step format).
“Common” is measured: kept by at least 6 in 10 of the 6 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
Task Planning Skill
Produces exactly one active docs/ai-context/TASK_PLAN.md (template:
templates/task/TASK_PLAN.md in the plugin) from either a prepared plan or
a plain
description. The plan is repository-aware: every stated path and fact is
verified or explicitly marked for verification.
When to Use
- The
startaction, with either input type. - Resuming a
planning-stage workflow.
Inputs
- Raw user input (ready plan or description).
docs/ai-context/PROJECT_CONTEXT.md,docs/ai-context/FEATURE_CHANGELOG.md(searched via the feature-changelog skill before writing the plan).- Detection facts (
bin/frappe-workflow detect --json), current Git state.
Outputs
docs/ai-context/TASK_PLAN.mdpassingbin/frappe-workflow validate task-plan(references/plan-validation.md).- Frontmatter filled: deterministic
task_id(TASK-YYYY-NNN — next number from prior plans/Git history, never reusing a found ID; start at 001 when none found),task_type,status: planned, app/bench/site facts,suggested_branch,related_features.
Procedure
- Active-task rule: an unfinished task is never silently replaced — the frappe-task router enforces this before delegating here.
- Feature search first (existing-feature-analysis.md).
- For ready plans: treat as input, not truth — verify every path, add missing technical/validation/security/migration steps, convert to the standard format; report every correction made.
- For descriptions: analyze the repository, then draft the full plan.
- For
task_type: project, additionally follow complete-project-planning.md. - Every implementation step must be specific and verifiable (template step format). Vague steps ("Update backend") are forbidden.
- Validate, then hand back to the router for the planning gate.
Preconditions
- Detection succeeded; no unfinished active task.
Stopping Conditions
- Plan validates and the user has seen it (plus the corrections list for ready plans) → done; implementation starts only after the planning gate.
- Input intent unclear (not a development task) → ask, don't guess.
Prohibited
- Silently changing the business objective, adding unrelated features, or expanding product scope (allowed silently: path corrections, missing technical validation, security/migration steps — each recorded).
- Starting implementation before the plan is complete and accepted.
- Inventing paths, DocTypes, or Sites — unverified locations say
Requires repository verification.
Shared Rules
shared-workflow-rules.md, frappe-project-detection.md.
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.

