agentleFS
farukzahrafarukzahra/agent-skills/skills/dont-forget/SKILL.md

dont-forget

Skill0 starsChanged 2 months agoMITView on GitHub

Turn recurring obligations into executable automation (CI, hooks, scripts, codegen, lint) instead of prose reminders agents may skip. Use when the user asks to always, never forget, every time, on each deploy, before commit, or when a task was forgotten repeatedly and needs hard enforcement.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 7 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    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
  1. Distinctive:

    Default: when the user asks for something that must happen repeatedly or was forgotten before, encode it in executable machinery the next …

    line 15
  2. Distinctive:

    Wait for user approval or adjustment: Do not implement until the user confirms.

    line 64
  3. Distinctive:

    README.md: when operators without agents need it

    line 70
  4. Distinctive:

    Never a paragraph asking future agents to remember

    line 71
  5. Very specific:

    Add scripts/increment-deploy-count.sh (or inline in workflow).

    line 147
  6. Very specific:

    Call it in .github/workflows/deploy.yml after successful deploy.

    line 148
  7. Very specific:

    Commit deploy-count.json (or expose via API).

    line 149
  8. Distinctive:

    Don't: Add only a user rule saying "remember to increment deploy count."

    line 152
  9. Distinctive:

    After implementation (post-approval confirmation — not a substitute for the pre-implementation proposal), state:

    line 156
  10. Distinctive:

    What fails: if skipped

    line 160

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Don't forget — obligation as automation

Agents forget. Written rules and chat promises are soft — they compete with context, get skipped under pressure, and vanish in new sessions.

Default: when the user asks for something that must happen repeatedly or was forgotten before, encode it in executable machinery the next agent cannot bypass without breaking the build.

The agent picks the highest tier that fits this repo — CI step, hook, failing test, codegen diff, npm script chain, etc. The "software" is whatever executable gate matches the obligation and trigger; not a fixed recipe.

Not "AI safety guardrails" — enforcement: repo machinery that fails when an obligation was skipped.

When to use

  • User says: always, every time, never forget, on each deploy, before every commit, don't let this slip again
  • Same instruction was given in a prior session and not followed
  • A counter, check, sync step, or enforcement must survive session handoff
  • User prefers "put it in the build" over "remember to do X"

When NOT to use

  • One-off task in the current session only
  • Judgment-heavy work (copy tone, architecture tradeoffs) with no objective pass/fail
  • Automation cost exceeds value (5-minute yearly task)
  • User explicitly wants a manual checklist only

Enforcement ladder (prefer top)

TierMechanismSurvives new chat?Example
1CI / deploy pipelineYesBump deploy counter in GitHub Actions
2Git hooks (pre-commit, pre-push)YesBlock commit if DER not updated
3Build / test failureYesmake der-check in CI
4Lint / type rulesYesESLint rule, custom Ruff check
5Codegen / scaffolderYesnpm run generate:api writes client from OpenAPI
6Scheduled jobYesCron syncs inventory nightly
7Cursor hook / project rulePartial.cursor/hooks.json runs validator on save
8Makefile / npm scriptPartialnpm run deploy chains all required steps
9Prose rule (AGENTS.md, SKILL.md)WeakLast resort or supplement to tiers 1–8

Pick the highest tier that fits. Add a prose rule only to point at the automation, not replace it.

Workflow

  1. Name the obligation — one sentence, observable outcome ("deploy counter increments on every production deploy").
  2. Find the natural trigger — deploy, commit, push, PR merge, file save, schedule, API call.
  3. Choose enforcement tier from the ladder above. 3b. Propose to user (before any file edits) — Present in plain language:

    • The obligation (one sentence, observable)
    • The trigger (deploy, commit, PR, schedule, etc.)
    • Chosen mechanism and tier (e.g. "GitHub Actions step after deploy — tier 1")
    • Files to create or change
    • What fails or blocks if the obligation is skipped
    • Optional: one-line AGENTS.md pointer you will add after implementation

    Wait for user approval or adjustment. Do not implement until the user confirms.

  4. After user approval, implement the smallest hard gate — script that exits non-zero, generated file diff, or pipeline step that fails.
  5. Wire the trigger — hook, workflow, package.json script chain, Makefile deploy target.
  6. Verify — run the trigger locally; confirm failure when obligation is skipped and success when met.
  7. Document briefly — one line pointing at the automation:
    • AGENTS.md (preferred in Cursor/agent repos): e.g. Deploy counter: auto-incremented in .github/workflows/deploy.yml
    • README.md when operators without agents need it
    • Never a paragraph asking future agents to remember

Decision checklist

Before finishing, confirm:

  • Obligation is tied to a concrete event (not "sometimes")
  • Skipping it causes visible failure (red CI, blocked commit, test fail) OR automatic correction (codegen)
  • A new agent can discover it from repo files, not chat history
  • User saw and approved the enforcement proposal before code changed
  • User was not given "I'll remember" without code

Patterns by domain

Deploy / release

  • GitHub Actions step after successful deploy
  • Release script that bumps version + changelog + counter in one command
  • Tag hook that refuses tag if checklist script fails

Commits / PRs

  • pre-commit: format, secrets scan, schema ↔ DER sync
  • PR CI: required check that cannot be skipped
  • Danger / custom bot comment is weak — prefer failing check

Schema / docs drift

  • Codegen from single source of truth (OpenAPI → client, SQL → types)
  • make check compares generated output to committed files
  • Fail CI if database/schema.sql changed but database/der.md did not

Environment / ports / health

  • docker-compose healthcheck + depends_on: condition: service_healthy
  • Startup script that probes /health before reporting URL to user
  • .env.example validated by script in CI

Agent-specific enforcement

  • Cursor hook on afterFileEdit running project validator
  • .cursor/rules that say run npm run verify-x, not "remember to verify"
  • Project skill with disable-model-invocation: false only when prose truly helps

Recurring maintenance

  • cron / GitHub scheduled workflow
  • Dependabot + auto-merge with passing CI
  • Stale-issue bot is notification-only — prefer workflow that does the sync

Anti-patterns

BadBetter
"I'll increment the counter next deploy"Step in deploy.yml increments deploy-count.txt
Long AGENTS.md section repeating the same reminderpre-commit + one-line pointer
Optional npm script nobody runsdeploy script calls it; CI runs deploy --dry-run
Comment // TODO: don't forget XTest or lint that fails until X exists

Example (deploy counter)

User: "Increment a counter every deploy — you forgot three times."

Propose (before coding):

Obligation: deploy-count.json increments on every successful production deploy. Trigger: GitHub Actions deploy workflow, after health check passes. Mechanism: Tier 1 — workflow step runs scripts/increment-deploy-count.sh and commits or updates the counter file. Files: .github/workflows/deploy.yml, scripts/increment-deploy-count.sh, deploy-count.json If skipped: deploy job fails (or counter stays stale — prefer failing the step). AGENTS.md line: Deploy count: see .github/workflows/deploy.yml

Approve to implement?

Do:

  1. Add scripts/increment-deploy-count.sh (or inline in workflow).
  2. Call it in .github/workflows/deploy.yml after successful deploy.
  3. Commit deploy-count.json (or expose via API).
  4. AGENTS.md: Deploy count: see .github/workflows/deploy.yml

Don't: Add only a user rule saying "remember to increment deploy count."

Report to user

After implementation (post-approval confirmation — not a substitute for the pre-implementation proposal), state:

  1. What is enforced
  2. Where (file + trigger)
  3. What fails if skipped
  4. That future sessions do not rely on memory

Additional examples

See reference/examples.md for more scenarios and tier choices.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.