reliable-execution
Skill0 starsChanged 10 days agoMITView on GitHub
Execute well-scoped non-trivial tasks the way the user expects — plan before acting, stay in scope, verify before reporting. Load once the task is sufficiently specified; if the request is vague, under-specified, or missing required context, invoke task-intake first. Also use when a session is long or a model tends to drift. Forces task restatement, step decomposition, scope checks, and honest reporting so the delivery matches the request.
In this repository34 other files it gives its agents.
- chatgpt/AGENTS.mdAGENTS.md
- opencode/AGENTS.mdAGENTS.md
- zcode/AGENTS.mdAGENTS.md
- claude/CLAUDE.mdCLAUDE.md
- agent-doc-authoringSkill
- agent-experienceSkill
- ai-image-promptsSkill
- api-behavior-flowSkill
- architecture-and-performanceSkill
- behavioral-testingSkill
- behavior-auditSkill
- browser-tabs-uiSkill
- code-qualitySkill
- context-compactSkill
- design-principlesSkill
- design-to-deliverySkill
- design-validationSkill
- e2e-test-authoringSkill
- engineering-reviewSkill
- excalidrawSkill
- external-ai-consultSkill
- google-omni-videoSkill
- llm-agent-tool-disciplineSkill
- parallel-subagentsSkill
- qa-test-scenariosSkill
- research-and-reuseSkill
- server-security-hardeningSkill
- session-handoffSkill
- shadcn-librarySkill
- sudo-handoffSkill
- task-intakeSkill
- tauri-v2-docsSkill
- test-failure-triageSkill
- user-behavior-flowSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
14 rules. About 0 are common, 12 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈12
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 25
Before starting any task that involves more than a one-line change.
- Very specific: line 26
When a well-specified request is large or spans multiple files (for vague or under-specified requests, run task-intake first).
- Distinctive: line 28
When the session is long and drift risk is high.
- Very specific: line 35
Restate the task in one sentence: If you cannot restate it, re-read the request before doing anything.
- Distinctive: line 36
Name the deliverable: Write down what "done" looks like.
- Distinctive: line 39
Execute in scope: Only what was asked. Note unrelated findings separately.
- Distinctive: line 40
Re-read the original request: Check off every requirement.
- Distinctive: line 41
Verify: Run the relevant checks (typecheck, lint, tests, or a manual test of the affected flow).
- Distinctive: line 47
Never add unrequested work to the delivery.
- Distinctive: line 48
Prefer the smallest change that satisfies the requirement.
- Distinctive: line 49
Keep restatement, acceptance criteria and planning internal unless a plan is requested.
- Distinctive: line 51
Never present unverified work as done.
- Distinctive: line 63
Every "done" claim is backed by a verification step.
- Distinctive: line 64
No file outside the request was modified.
≈ “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
Reliable Execution — Universal
Persistent design workflow companion
For complex feature/screen/API/architecture design, consider design-to-delivery as an adaptable playbook. Its diagram → brainstorming → docs/specs/<work-id>/specs.md → docs/task/<work-id>/tasks.md sequence helps expose missing states, contract inconsistencies and verification gaps. Choose or simplify the useful parts; ordinary design requests do not require every artifact. Explicitly requested documents remain deliverables and the internal-planning rule below does not suppress them. Continue authorized implementation using the selected plan without duplication. Preserve all existing documents and history.
Purpose
Turn any request into an on-scope, verifiable delivery. Especially valuable for models that tend to drift mid-task: it forces restatement, decomposition, scope discipline, and honest reporting.
When to use
- Before starting any task that involves more than a one-line change.
- When a well-specified request is large or spans multiple files (for vague
or under-specified requests, run
task-intakefirst). - When the session is long and drift risk is high.
Preconditions
- The original request is available to re-read (do not rely on memory of it).
- Verification commands for the project are known or discoverable (package.json scripts, Makefile, CI config).
Workflow
- Restate the task in one sentence. If you cannot restate it, re-read the request before doing anything. For vague or under-specified requests, run the
task-intakeskill first to build the brief. - Name the deliverable. Write down what "done" looks like.
- Decompose into steps. Break the work into the smallest number of concrete steps that cover the whole request; order them.
- Gate each step. Execute work already authorized by the request, including large reversible tasks. Ask only for destructive/irreversible actions, missing required authorization, blocking ambiguity, or a materially broader outcome; size alone is not an approval gate.
- Execute in scope. Only what was asked. Note unrelated findings separately; do not fix them.
- Re-read the original request. Check off every requirement; complete anything missing.
- Verify. Run the relevant checks (typecheck, lint, tests, or a manual test of the affected flow).
- Report. What changed, what was verified, what failed or is uncertain — in that shape.
Rules
- Work like a maintainer: derive code style from explicit project conventions and maintained approved examples, including naming, module boundaries, errors and test/helper style. Preserve understandable diffs and existing behavior; do not imitate known defects or claim to know unrecorded personal preferences. Use proportional self-review before handing meaningful changes back. Flexible process is not a reason to omit care or hide verification gaps.
- Ambiguity that changes the outcome → ask. An obvious, safe, reversible default → proceed and state it.
- Never add unrequested work to the delivery; report it as a separate note.
- Prefer the smallest change that satisfies the requirement; preserve existing behavior.
- Keep restatement, acceptance criteria and planning internal unless a plan is requested. Preserve useful existing content when improving instruction files; do not replace an improvement request with a shortening campaign.
- Before edits, read the current target and related contracts; afterward re-read and inspect the diff. For behavior changes use
behavioral-testing, for E2E use the project skill ore2e-test-authoring, for non-trivial self-review useengineering-review, and for static checks usecode-quality. These are companions, not duplicate execution plans. - Never present unverified work as done. If you could not verify, say so plainly.
- Reversible bias: prefer additive changes over replacements; backup before irreversible operations.
Common mistakes
- Starting to code before restating the task — this is where drift begins.
- "Also fixing" unrelated issues noticed along the way.
- Reporting success without running verification.
- Asking the user when the default is obvious — wastes their time.
- Expanding scope to make the solution "nicer" instead of delivering what was asked.
Validation
- The final report maps 1:1 to the original request.
- Every "done" claim is backed by a verification step.
- No file outside the request was modified.
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.

