plan-to-execution-handoff
Skill1 starsChanged 32 days agoMITView on GitHub
Convert an approved plan into scoped work items, dependencies, acceptance checks and a durable handoff for the available execution workflow.
In this repository42 other files it gives its agents.
- ansible-hardeningSkill
- cavetechSkill
- ci-cdSkill
- claude-to-cursorSkill
- code-consistencySkill
- code-qualitySkill
- config-auditorSkill
- container-sandboxSkill
- cpa-tax-specialistSkill
- database-designSkill
- definition-of-doneSkill
- differential-reviewSkill
- exact-head-reviewSkill
- fast-ciSkill
- grill-meSkill
- inbound-syncSkill
- infosec-architectSkill
- insecure-defaultsSkill
- lonely-sysadminSkill
- mcp-createSkill
- mcp-hardeningSkill
- model-evaluationSkill
- modern-pythonSkill
- ms-office-suiteSkill
- mutation-checkSkill
- prd-to-planSkill
- property-based-testingSkill
- pr-truth-triageSkill
- repo-hardening-workflowSkill
- resume-writerSkill
- skill-updaterSkill
- software-developerSkill
- software-development-lifecycleSkill
- solutions-architectSkill
- stay-readySkill
- supply-chain-risk-auditorSkill
- systematic-debuggingSkill
- tddSkill
- token-miserSkill
- triage-issueSkill
- verification-before-completionSkill
- write-a-prdSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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
- Very specific: line 13
Use the repository's existing task schema.
≈ “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
Approved plan to execution handoff
Identify the approved plan and its exact revision. Do not select an arbitrary recently modified plan. Read current source and related work to avoid duplicating implementation or overriding active ownership.
For each work item capture ID, requirement, scope, owner, dependencies, acceptance checks, expected evidence, rollback constraints and status. Split work into complete vertical slices. Assign compute/platform requirements only from known needs and available capacity; do not invent hosts or lanes.
Validate unique IDs, all dependency references and absence of cycles. A plan can legitimately have every item blocked by an external dependency: report that instead of inventing ready work. Missing estimates stay unknown; do not derive time promises from keywords.
Use the repository's existing task schema. If none exists, a human-readable handoff under plans/ can contain:
schema_version: 1
source_plan: plans/approved-plan.md
source_revision: FULL_REVISION
items:
- id: item-1
title: Implement the agreed consumer path
status: pending
owner: unassigned
requires: []
acceptance:
- Describe an observable, reproducible pass/fail check
evidence: []
rollback: Describe applicable recovery constraintsThis is a documentation schema, not a claim that an executor can ingest it. Confirm the receiving tool's contract before automation. Execute independent authorized ready work through software-development-lifecycle; record blockers and exact next actions. Do not dispatch agents, spend money, merge or deploy solely because a handoff exists.
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.

