task-dispatch
Skill0 starsChanged 22 days agoMITView on GitHub
Decide whether a task requires direct work, one specialised capability, or high-complexity planning and independent reviews.
- Commits and pushes
2 other projects use a version of this.
Adopted by
Most recently taken up by
- HACK-WU/skillstheir own version, first seen Sep 25, 2026
- Number-2222/task-dispatchtheir own version, first seen Aug 7, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- HACK-WU/skills★ 3same name
- Number-2222/task-dispatch★ 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 repository33 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/setup-project-context/templates/CLAUDE.mdCLAUDE.md
- backend-architectureSkill
- build-review-loopSkill
- capability-intakeSkill
- competitor-market-analysisSkill
- context-auditSkill
- data-analysis-insightsSkill
- data-privacy-securitySkill
- dev-agentsSkill
- dev-patternsSkill
- frontend-system-designSkill
- idea-validatorSkill
- intellectual-property-licensingSkill
- international-legal-researchSkill
- legal-document-drafterSkill
- llm-councilSkill
- make-slidesSkill
- password-authentication-securitySkill
- privacy-data-protection-lawSkill
- project-estimation-planningSkill
- project-startSkill
- rea-researchSkill
- requirements-business-analystSkill
- secrets-credential-managerSkill
- seo-tech-stackSkill
- setup-project-contextSkill
- shopify-ui-auditSkill
- site-incidentSkill
- sop-process-builderSkill
- technical-feasibilitySkill
- tech-research-intelligenceSkill
- update-mdSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
19 rules. About 0 are common, 16 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈16
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 34
If direct work is sufficient: use no extra skill, MCP, plugin or agent.
- Very specific: line 35
If specialised capability is required: read only the relevant section of ~/.claude/capability-registry.md, read ~/.claude/agent.md only …
- Distinctive: line 36
If complexity is below 80: proceed directly or with one required capability, perform relevant verification.
- Distinctive: line 37
If complexity is 80+: state that work is high complexity, produce a short plan before major changes, use only necessary implementation …
- Distinctive: line 41
When a task references another project, clone, migration, white-label build, imported content, fetched data, shared module or database …
- Distinctive: line 44
Treat the source project as reference-only by default.
- Distinctive: line 45
Do not copy data or use another project's database without explicit approval.
- Distinctive: line 51
When a task involves git push, release, merge, version tag, deployment, rollback or production movement:
- Distinctive: line 53
Treat it as sensitive and require explicit instruction before write actions.
- Very specific: line 54
Read <project>/docs/16-DEPLOYMENT.md (+ its .local.md.
- Distinctive: line 55
Do not invent branch, release, version, tag, server or deployment details.
- Distinctive: line 56
Use only required git or deployment capability after approval.
- Very specific: line 58
After actual release or deployment, add a release entry to docs/17-CHANGELOG.md and update docs/01-PRD.md §Scope status only where relevant …
- Distinctive: line 62
Do not inspect the complete skill, plugin, MCP or agent inventory.
- Distinctive: line 63
Do not invoke capability merely because it exists.
- Distinctive: line 64
Do not call several similar capabilities to compare results by default.
- Distinctive: line 65
Do not invoke deployment capability without explicit deployment instruction.
- Distinctive: line 66
Do not invoke gstack or external packs unless the current required workflow justifies it.
- Distinctive: line 70
Only when specialised capability or high-complexity process is required, report:
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Minimum Capability Task Dispatch
Requested task: $ARGUMENTS
Objective
Choose the smallest sufficient execution path without loading or invoking unrelated capabilities.
Do Not Use This Skill For
update md,update docs,save progress,update tasksor progress recording.- Simple project resolution handled by
project-start. - New capability review handled by
capability-intake.
Decision Process
- Identify the exact requested outcome.
- Identify the active project and affected work area.
- Determine whether direct work is sufficient.
- Assess task complexity internally from 0 to 100 using:
- Number of modules affected.
- Business-critical logic.
- Authentication, permissions, finance, payments or sensitive-data impact.
- External integrations.
- Database or schema changes.
- Production risk.
- Unknowns, reversibility and regression risk.
- If direct work is sufficient: use no extra skill, MCP, plugin or agent.
- If specialised capability is required: read only the relevant section of
~/.claude/capability-registry.md, read~/.claude/agent.mdonly when delegated review or execution is required, choose the smallest suitable capability, do not choose overlapping capabilities for the same purpose. - If complexity is below 80: proceed directly or with one required capability, perform relevant verification.
- If complexity is 80+: state that work is high complexity, produce a short plan before major changes, use only necessary implementation capability, perform actual relevant verification, complete two independent review passes, resolve or report issues before declaring completion.
Cross-Project Data Check
When a task references another project, clone, migration, white-label build, imported content, fetched data, shared module or database reuse:
- Read
~/.claude/references/cross-project-data-copy.md. - Treat the source project as reference-only by default.
- Do not copy data or use another project's database without explicit approval.
- Continue only with structure, logic or placeholder implementation where transfer is not approved.
- Increase risk assessment when private data, databases, credentials or production records are involved.
Release, Git Push and Deployment Check
When a task involves git push, release, merge, version tag, deployment, rollback or production movement:
- Treat it as sensitive and require explicit instruction before write actions.
- Read
<project>/docs/16-DEPLOYMENT.md(+ its.local.md; unmigrated:docs/deploy.md) before proceeding. - Do not invent branch, release, version, tag, server or deployment details.
- Use only required git or deployment capability after approval.
- For a major release, require an approved version tag before pushing or releasing.
- After actual release or deployment, add a release entry to
docs/17-CHANGELOG.mdand updatedocs/01-PRD.md§Scope status only where relevant (unmigrated:docs/changelog.md,docs/completed-vs-scope.md).
Capability Restriction
- Do not inspect the complete skill, plugin, MCP or agent inventory.
- Do not invoke capability merely because it exists.
- Do not call several similar capabilities to compare results by default.
- Do not invoke deployment capability without explicit deployment instruction.
- Do not invoke gstack or external packs unless the current required workflow justifies it.
Dispatch Output
Only when specialised capability or high-complexity process is required, report:
Execution path: <Specialised capability / High-complexity workflow>
Complexity: <score only for substantial work or when 80+ rule applies>
Capability selected: <capability name only when selected>
Reason: <one concise line>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.

