agentleFS
Baba01hacker666Baba01hacker666/dummyskills/skills/status-update/SKILL.md

status-update

Skill0 starsChanged 2 months agoMITView on GitHub

Produces a concise, fact-checked progress update based strictly on observed execution evidence.

11 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Show its rules and text

We split this skill into the rules it gives an agent

14 rules. 0 are common, 8 are distinctive, and 6 are very specific to this project.

  • 0

    Common

    Most of the 11 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 6

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when:

    line 14
  2. Very specific:

    Do not use to write end-user feature release notes.

    line 20
  3. Very specific:

    Do not use to plan upcoming tasks.

    line 21
  4. Very specific:

    Do not use to diagnose why a command failed.

    line 22
  5. Distinctive:

    If no completed actions or evidence is provided: state "No verified progress completed yet."

    line 31
  6. Distinctive:

    Never claim an item is completed unless command output or file inspection confirmed it.

    line 32
  7. Distinctive:

    If blockers are unknown, explicitly check test status before marking "None".

    line 33
  8. Distinctive:

    Follow these numbered actions:

    line 36
  9. Distinctive:

    Write 2 to 4 bullet points referencing specific files or tests.

    line 42
  10. Distinctive:

    If blocked, state the exact error and required decision.

    line 44
  11. Very specific:

    If any test failed during work: state BLOCKED or IN PROGRESS (Tests Failing).

    line 49
  12. Very specific:

    If user input is required to proceed: mark state as BLOCKED (Needs Input).

    line 50
  13. Very specific:

    If all steps and tests passed: mark state as COMPLETED.

    line 51
  14. Distinctive:

    Stop and escalate when:

    line 85

“Common” is measured: kept by at least 6 in 10 of the 11 edited versions of this file we could read. “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

Status Update

Generates a clear, structured progress update based solely on verified commands and observable outputs. Prevents misleading or optimistic status claims.

1. Purpose

Report progress truthfully to human operators or peer agents. A "status update" summarizes what was accomplished, what is in flight, blockers, and next steps with verifiable proof.

2. When to Use

Use this skill when:

  • Reaching a task milestone or completing execution steps.
  • Handing off work to another agent or human.
  • A user asks "Where do things stand?" or "What's the status?".

3. When Not to Use

  • Do not use to write end-user feature release notes; use release-notes-drafter.
  • Do not use to plan upcoming tasks; use task-brief.
  • Do not use to diagnose why a command failed; use command-failure-diagnoser.

4. Required Inputs

  • task_title: The name of the task or ticket being worked on.
  • completed_evidence: List of completed actions with command output or file diff proof.
  • blockers: Any errors, missing info, or roadblocks encountered (or "None").
  • next_actions: Planned immediate next steps.

5. Missing-Input Behavior

  1. If no completed actions or evidence is provided: state "No verified progress completed yet."
  2. Never claim an item is completed unless command output or file inspection confirmed it.
  3. If blockers are unknown, explicitly check test status before marking "None".

6. Procedure

Follow these numbered actions:

  1. Action 1: Verify Evidence
    • For every claimed completion, check for supporting evidence (e.g. exit code 0, file created).
  2. Action 2: Classify Overall State
    • Select state: ON TRACK, BLOCKED, or COMPLETED.
  3. Action 3: Summarize What Was Done
    • Write 2 to 4 bullet points referencing specific files or tests.
  4. Action 4: Document Blockers and Mitigations
    • If blocked, state the exact error and required decision.
  5. Action 5: Emit Status Update
    • Format using Section 8.

7. Decision Rules

  • If any test failed during work: state BLOCKED or IN PROGRESS (Tests Failing); never state COMPLETED.
  • If user input is required to proceed: mark state as BLOCKED (Needs Input).
  • If all steps and tests passed: mark state as COMPLETED.

8. Output Format

Emit the status update using this structured template:

### Status Update: [Task Title]

- **Current State**: [COMPLETED | ON TRACK | BLOCKED]
- **Milestone Progress**: [e.g., 2 of 3 steps verified]

#### What Was Completed
- [Action 1 with evidence, e.g., Created `src/auth.ts`, linter passed]
- [Action 2 with evidence]

#### Blockers & Roadblocks
- [None, or exact blocking error and what is needed]

#### Next Immediate Action
- [Next single testable step]

9. Verification Checklist

  • Every completed item lists concrete evidence.
  • Status is not claimed as COMPLETED if tests are red.
  • Next action is concrete and singular.
  • No internal hidden reasoning leaked.

10. Common Failures and Recovery

Failure SymptomCauseRecovery Action
Optimistic completionMarking done before tests runCheck git status and test command output first.
Vague blockerSaying "build failed" without detailPaste exact compiler error line in blocker section.

11. Stop or Escalation Conditions

Stop and escalate when:

  • State is BLOCKED for more than 2 attempts on the same issue.
  • Missing credentials or permissions prevent verification.

12. Examples

Example 1: Successful Execution

Input:

Task: Fix null pointer in billing.ts.
Evidence: Modified billing.ts to check for undefined user. Ran `npm test tests/billing.test.ts` (3 passed, 0 failed).
Blockers: None.
Next: Open pull request.

Output:

### Status Update: Fix null pointer in billing.ts

- **Current State**: COMPLETED
- **Milestone Progress**: 1 of 1 fix completed

#### What Was Completed
- Added undefined guard to `user.subscription` in `src/billing.ts`.
- Verified regression test: `npm test tests/billing.test.ts` passed (3 tests green).

#### Blockers & Roadblocks
- None.

#### Next Immediate Action
- Ready for PR submission or code review.

Example 2: Ambiguous or Missing Input

Input:

Task: "Database migration" (No evidence provided)

Output:

### Status Update: Database migration

- **Current State**: ON TRACK (Pending verification)
- **Milestone Progress**: 0 verified steps

#### What Was Completed
- No verified completions reported yet.

#### Blockers & Roadblocks
- Needs execution log or migration command output to verify database state.

#### Next Immediate Action
- Inspect migration runner log to confirm migration applied cleanly.

Example 3: Expected Final Output

Output:

### Status Update: Upgrade Node.js runtime

- **Current State**: BLOCKED
- **Milestone Progress**: 1 of 3 steps complete

#### What Was Completed
- Updated `.nvmrc` and `package.json` engines to Node 22.

#### Blockers & Roadblocks
- `npm install` fails due to deprecated native binding in `legacy-crypto` package. Needs approval to upgrade or replace `legacy-crypto`.

#### Next Immediate Action
- Await user guidance on replacing `legacy-crypto`.

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.