spec-exec
Skill0 starsChanged 9 months agoApache-2.0View on GitHub
Execute a provided specification completely in one shot. The spec defines WHAT. Your job is HOW. Keep main context clean. Delegate aggressively.
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
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 19
No gold-plating: - don't add unrequested features
- Distinctive: line 22
After each implementation unit, verify via exit codes and test output, not assumptions:
- Distinctive: line 29
Use Task tool for:
- Distinctive: line 34
Keep main context clean. Delegate aggressively.
- Distinctive: line 64
Verify at each step
- Distinctive: line 66
Don't interpret - execute
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
Spec Exec Skill
Execute a provided specification completely in one shot.
Input
A structured specification that defines:
- What to build
- Acceptance criteria
- Constraints
The spec defines WHAT. Your job is HOW.
Execution Rules
No Deviation
- No clarifying questions - the spec is complete
- No scope expansion - exactly what's specified
- No partial completion - finish or report blockers
- No gold-plating - don't add unrequested features
Verification Required
After each implementation unit, verify via exit codes and test output, not assumptions:
- Run tests
- Verify lint
- Check build
- Only then continue
Sub-Agent Usage
Use Task tool for:
- Parallel independent work
- Exploration that doesn't need your context
- Bounded subtasks with clear deliverables
Keep main context clean. Delegate aggressively.
Output Format
At completion:
## Spec Executed
<brief summary>
## Files Created/Modified
| File | Action | Lines |
|------|--------|-------|
## Commands Run
| Command | Exit Code |
|---------|-----------|
## Test Results
- Total: <count>
- Passed: <count>
- Failed: <count>
## Blockers Encountered
<any issues that prevented completion>
## Deviations from Spec
<any necessary changes, with justification>Rules
- Complete the entire spec
- Verify at each step
- Report blockers immediately
- Don't interpret - execute
In this repository21 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- auto-linterSkill
- changelogSkill
- commitSkill
- debugSkill
- docsSkill
- exploreSkill
- featureSkill
- fixSkill
- forensicSkill
- openq-toolsSkill
- policy-runnerSkill
- pr-createSkill
- pr-prepSkill
- refactorSkill
- reviewSkill
- runs-deriveSkill
- runs-indexSkill
- secrets-toolsSkill
- test-runnerSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.