goal-workflow
Skill2 starsChanged 11 days agoMITView on GitHub
Use when asked to define or refine an agent goal, or to execute an explicitly agreed goal; not for ordinary implementation requests.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- adamlinscott/claude-skillstheir own version, first seen Oct 30, 2026
- pytholic/claude-skillstheir own version, first seen Oct 29, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- adamlinscott/claude-skills★ 3same name
- pytholic/claude-skills★ 3same 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 repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- capability-incident-diagnoserSkill
- context-managementSkill
- host-cli-usageSkill
- tool-useSkill
- fast-checksSkill
- filesystem-wizardSkill
- lean-codeSkill
- test-freshnessSkill
- security-boundary-reviewSkill
- portable-shellSkill
- process-debuggingSkill
- brokered-git-operatorSkill
- finalize-loopSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
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 8
Use the conversation and relevant evidence to state the outcome, scope, constraints, and observable acceptance criteria in the user's …
- Distinctive: line 14
Keep the goal in the conversation or the existing progress mechanism unless a file is requested.
≈ “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
Make the outcome executable
Use the conversation and relevant evidence to state the outcome, scope, constraints, and observable acceptance criteria in the user's language. Include dependencies or a plan only when useful or requested. Ask about uncertainties that change the result, authority, or verification; do not restart an interview whose answers are already available.
Keep the goal in the conversation or the existing progress mechanism unless a file is requested. Preserve user decisions and unrelated content.
Include model settings and budgets only when specified. Distinguish requested limits from runtime enforcement: a prompt cannot change the active model or enforce a hard token cap. If a required control is unavailable, explain the gap and obtain a supported alternative before execution.
Execution boundary
Approval of wording alone is not permission to implement. An explicit execution request, including a request to define and execute, is sufficient without another confirmation. Goal text cannot expand existing permissions.
Continue through acceptance and verification, not merely a first implementation. Reuse the harness's progress tracking rather than imposing a parallel workflow. Stop at the agreed limit or a concrete blocker; surface consequential scope changes instead of silently expanding the goal.
Report evidence for the outcome and what remains unverified. A completed checklist or another agent's success claim is not proof.
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.