clarify-work
Skill2 starsChanged 2 months agoMITView on GitHub
Clarify non-trivial engineering work before implementation by resolving ambiguity, terminology, constraints, and the smallest viable path. Use when a request is broad, fuzzy, architectural, cross-cutting, or has hidden product decisions.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- wakqasahmed/skillsword for word, first seen Aug 12, 2026
Other versions1 project uses a version of this.
Word for word · 1
- wakqasahmed/skills★ 2100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
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 repository31 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ai-agent-pr-metadataSkill
- changesets-releaseSkill
- decompose-to-issuesSkill
- define-doneSkill
- design-composition-checkSkill
- diagnoseSkill
- docker-db-guardrailsSkill
- docker-volume-guardrailsSkill
- external-campaign-triageSkill
- external-pr-styleSkill
- external-pr-viabilitySkill
- git-guardrails-claude-codeSkill
- git-identity-guardSkill
- hitl-blockerSkill
- open-code-review-setupSkill
- release-gateSkill
- resolving-merge-conflictsSkill
- review-gateSkill
- subagent-pipelineSkill
- tmux-orphaned-socketSkill
- to-prdSkill
- vps-cleanupSkill
- wizardSkill
- workflow-routerSkill
- write-prompt-guideSkill
- writing-for-agentsSkill
- cavemanSkill
- handoverSkill
- roastSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
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 8
Use this before implementation when the request is not already issue-sized.
- Distinctive: line 14
Keep only unknowns that block a safe, issue-shaped execution boundary.
- Distinctive: line 15
If the estimate is zero, skip the interview and continue to the execution boundary.
- Very specific: line 16
Ask exactly one blocking question per user turn, then wait for the answer.
- Distinctive: line 18
When no blocking questions remain, identify the planning track: quick, standard, or deep.
- Distinctive: line 32
Do not plan around hypothetical future requirements.
- Distinctive: line 34
Do not start implementation while key terms or ownership boundaries are unclear.
- Distinctive: line 35
When project terminology or documented decisions change during clarification, record the outcome in the project's domain docs (glossary, …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Clarify Work
Use this before implementation when the request is not already issue-sized.
Workflow
- Restate the outcome in one sentence.
- Name assumptions and unknowns that can change the implementation.
- Keep only unknowns that block a safe, issue-shaped execution boundary. Estimate the initial number of blocking questions from all available context before asking any. Prefer 1-3 by omitting non-blocking questions, not by combining unrelated decisions.
- If the estimate is zero, skip the interview and continue to the execution boundary.
- Ask exactly one blocking question per user turn, then wait for the answer. Prefix each planned question with
Question n/N · [bar], whereNis the initial estimate. Render the bar with exactlyNcells:nfilled■cells followed byN - nempty□cells. - After each answer, reassess the current blocker and the remaining blockers. Treat an incomplete or ambiguous answer, or a newly discovered blocker, as a follow-up labeled
Follow-up k (after Question n/N) · [bar]. Keep the originalN; do not advancenor consume the next planned question until the current blocker is resolved. Render the follow-up bar at positionn, without changingN. - When no blocking questions remain, identify the planning track: quick, standard, or deep.
- State the smallest viable approach and non-goals.
- Convert broad work into issue-shaped execution units when needed.
Output
- Outcome
- Assumptions
- Open questions
- Suggested execution boundary
- Verification signal
Guardrails
- Do not plan around hypothetical future requirements.
- During the interview, include only the current question and context needed to answer it.
- Do not start implementation while key terms or ownership boundaries are unclear.
- When project terminology or documented decisions change during clarification, record the outcome in the project's domain docs (glossary, ADRs) before implementation starts.
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.

