implement
Skill67 starsChanged 4 months agoMITView on GitHub
Execute a pre-defined plan using implementation agents (no design changes)
191 other projects use a version of this.
Adopted by
Most recently taken up by
- revisit-studies/studytheir own version, first seen Nov 9, 2026
- dz114879/skillstheir own version, first seen Nov 8, 2026
- Dimon94/dveritytheir own version, first seen Nov 8, 2026
- Dimon94/skillstheir own version, first seen Nov 8, 2026
- The-Vibe-Company/quivrtheir own version, first seen Nov 8, 2026
- miklschmidt/archboardtheir own version, first seen Nov 8, 2026
Used with
Projects with it also use setup-ts-deep-modules, ask-matt 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.
liufeng1976Skillsetup-ts-deep-modules
Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.
Also in 43 projects that use this
GoogleSkillask-matt
Ask which skill or flow fits your situation. A router over the skills in this repo.
Also in 91 projects that use this
RoentekSkillloop-me
Grill me about specs for the workflows I want to build, within this workspace.
Also in 50 projects that use this
AWSSkillto-questionnaire
Turn a decision you can't fully answer into a questionnaire for someone else to fill in.
Also in 88 projects that use this
ryotaroh180105Skillclaude-handoff
Hand the current conversation off to a fresh background agent that picks up the work immediately.
Also in 42 projects that use this
- GoogleSkill
to-spec
Turn the current conversation into a spec and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.
Also in 168 projects that use this
- +3 more from google
Other versions191 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 191
- mattpocock/skills★ 309ksame name
- QuivrHQ/quivr★ 40ksame name
- The-Vibe-Company/quivr★ 40ksame name
- foambubble/foam★ 17ksame name
- formbricks/formbricks★ 13ksame name
- ArcReel/ArcReel★ 6.3ksame name
- vinvcn/mattpocock-skills-zh-CN★ 5.5ksame name
- fallow-rs/fallow★ 5.3ksame name
- withcoral/coral★ 4.9ksame name
- bestofjs/bestofjs★ 3.1ksame name
181 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 repository24 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- autoresearchSkill
- brainstormSkill
- bug-huntSkill
- check-resolvableSkill
- compSkill
- debugSkill
- dialectic-reviewSkill
- distillSkill
- finalizeSkill
- learnSkill
- plan-taskSkill
- premortemSkill
- red-teamSkill
- researchSkill
- retroSkill
- reviewSkill
- rsbSkill
- sessionsSkill
- shipSkill
- socratesSkill
- tradeoffSkill
- verifySkill
- wrapupSkill
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 6 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 171 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
If no arguments, look for the most recently discussed plan in the conversation.
- Distinctive: line 27
If no plan exists, STOP and tell the user: "No plan found.
- Distinctive: line 31
Read relevant COMP files (CLAUDE.md for conventions, MEMORY.md for gotchas)
- Distinctive: line 46
If a sub-task fails or hits an unexpected issue, STOP and report to the user rather than improvising a workaround
- Very specific: line 48
After each subagent returns, validate the report.
- Distinctive: line 51
Check the plan's success criteria:
- Distinctive: line 52
Run tests if applicable
- Very specific: line 60
After implementation completes, /verify is mandatory -- not optional.
“Common” is measured: kept by at least 6 in 10 of the 171 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
Implementation Agent
Execute a plan that has already been designed and approved. This is the "do" phase -- no redesigning.
Input
Plan to implement: $ARGUMENTS
If no arguments, look for the most recently discussed plan in the conversation.
Process
Step 1: Locate the Plan
Find the plan to implement. Sources:
- Explicitly provided in arguments
- Most recent /plan-task output in conversation
- Project PLAN.md
If no plan exists, STOP and tell the user: "No plan found. Run /plan-task first, or describe what to implement."
Step 2: Verify Prerequisites
Before starting:
- Read relevant COMP files (CLAUDE.md for conventions, MEMORY.md for gotchas)
- Confirm all dependencies are met
- Identify any sub-tasks that can run in parallel
Step 2.5: Triage Complexity
Assess the plan's scope and choose execution strategy:
- Trivial (single file, well-understood): Execute directly, skip subagents. Don't waste tokens on delegation overhead.
- Small (few files, clear spec): Execute directly or single subagent.
- Large (multi-file, cross-cutting, research needed): Decompose into sequential subagent dispatches with verification between each.
Step 3: Execute Sub-Tasks
Work through the plan's sub-tasks in order:
- For parallelizable tasks, use multiple Agent calls in a single message
- For each sub-task, verify completion before moving to the next dependent task
- If a sub-task fails or hits an unexpected issue, STOP and report to the user rather than improvising a workaround
After each subagent returns, validate the report. See ~/.claude/skills/implement/subagent-validation.md for the full protocol.
Step 4: Verify Success
Check the plan's success criteria:
- Run tests if applicable
- Generate visualizations if the plan called for them
- Spot-check outputs against expected values
Report results to the user.
See ~/.claude/skills/implement/rules.md for implementation guardrails.
After implementation completes, /verify is mandatory -- not optional. The /wrapup health check will flag sessions where /implement ran without /verify.
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.