New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Check Work

by Sidiora-Labs in Sidiora-Labs/centra-gideon-agent

Verify what you just claimed, with real tool calls — reconstruct the claims from this session, derive 2-4 executable checks from those specific claims, run every one, and report pass/fail with…

Apache-2.0Auto-check passedProductivity & Automation

Install Check Work

skills CLI
$ npx skills add Sidiora-Labs/centra-gideon-agent --skill check-work -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Sidiora-Labs/centra-gideon-agent check-work --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Sidiora-Labs/centra-gideon-agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/runtime/gideon/extensions/skills/bundled/check-work .claude/skills/check-work && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
check-work
GitHub stars
217
Token cost
~1.3k tokens
SKILL.md length
674 words
Files
2 (incl. references)
Skills in repo
24
Repo updated
First seen
Licence
Apache-2.0

At a glance

Verify what you just claimed, with real tool calls — reconstruct the claims from this session, derive 2-4 executable checks from those specific claims, run every one, and report pass/fail with…

  • Works in 4 steps: Reconstruct the claims (don't re-derive… → Derive 2-4 checks from those claims → Run them. Actually run them. → …
  • Tasks that involve Scheduled and recurring tasks
  • SKILL.md covers Step 1 — Reconstruct the…, Step 2 — Derive 2-4 checks…, Step 3 — Run them. Actually… and Step 4 — Report, plus 1 more section
  • Calls make, python and curl

What it does

Check Work is an agent skill from Sidiora-Labs/centra-gideon-agent. Verify what you just claimed, with real tool calls — reconstruct the claims from this session, derive 2-4 executable checks from those specific claims, run every one, and report pass/fail with quoted evidence. A check that cannot be executed is reported unverifiable, never assumed passing.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/qa-boundary.md`).

It sits in Productivity & Automation, covering Scheduled and recurring tasks. The repository describes itself as: The companion AI agent that learns, adapts and gets the work done no matter the task. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Scheduled and recurring tasks

Example prompts

  • “/check-work”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Reconstruct the claims (don't re-derive the task)
  2. Derive 2-4 checks from those claims
  3. Run them. Actually run them.
  4. Report

What it can do on your machine

Read from SKILL.md and the folder at commit ca531ee. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • make
    • python
    • curl

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Check Work loads about 1.3k tokens when it runs, and up to ~1.9k if it reads all its reference files. Until then it costs about 75 tokens; SKILL.md has 674 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~75
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Sidiora-Labs/centra-gideon-agent at commit ca531ee, republished under its Apache-2.0 licence (© Sidiora-Labs). 674 words, ~1,307 tokens.

Download SKILL.mdSave it as .claude/skills/check-work/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
check-work
description
Verify what you just claimed, with real tool calls — reconstruct the claims from this session, derive 2-4 executable checks from those specific claims, run every one, and report pass/fail with quoted evidence. A check that cannot be executed is reported unverifiable, never assumed passing.
always
false
triggers
check your work, check this work, verify that, verify this, did that actually work, are you sure, prove it, double check, confirm it works, did it work, is…

Check Work

You just told the user something was done. This skill answers a different question: is it? Not by re-reading your own message — by observing the artifacts your message claimed exist.

The one rule: every check is a tool call or it is unverifiable. There is no third option. You may never report a check as passing because it "should" pass, or because a related command passed earlier in the session. Ground truth over self-report — the same doctrine the loop judge runs on.

Step 1 — Reconstruct the claims (don't re-derive the task)

Read back over this session's recent turns and tool calls and write down what was claimed complete, in the claimer's own words. Quote them.

  • "Added derive_checks() to src/gideon/check_work.py" → a claim about a file's contents.
  • "make lint is clean" → a claim about a command's exit status.
  • "The endpoint returns the new field" → a claim about a running surface.
  • "I'll add tests next" → not a claim. Intent isn't a claim; skip it.

Claims come from the transcript, not from the task description. If the task said five things and the session claimed two, you check the two that were claimed.

Step 2 — Derive 2-4 checks from those claims

Each check must be a real command the user could run and watch pass or fail, and it must be traceable to a specific claim. Not a generic checklist — a checklist that would read the same for any session is a tell that you skipped step 1.

Claim shapeCheck shape
a file was written / editedtest -e <path>, then grep -n '<the thing claimed>' <path>
a command passesre-run that exact command (make lint, python -m pytest -n 0 --no-cov <file>)
an endpoint answerscall it (curl -s localhost:<port>/api/...) and read the body
something was deleted / renamedgrep -rn '<old name>' <tree> returns nothing
an artifact rendersfetch/open it and confirm the expected content is present

Prefer the content form over the existence form: grep for the symbol the claim named beats test -e, because an empty file passes test -e.

Two is the floor (one check is not a cross-check); four is the ceiling (past that you're writing a test suite, and the user asked for a check).

Only commands that exist in this repo. If you cannot name a real command for a claim, that claim is unverifiable — say so. Do not invent a script.

Show full SKILL.md (277 more words)Show less

Step 3 — Run them. Actually run them.

Execute each check with a real tool call and keep the output. Then classify:

  • pass — it ran and the observed output matches the claim. Evidence = the output line (src/gideon/check_work.py:196: def derive_checks(), not "confirmed".
  • fail — it ran and the output contradicts the claim. Evidence = the contradiction (no such file, 1 failed, exit 1, an empty grep).
  • unverifiable — it could not run here (no dev gateway up, no credentials, needs a browser, the path is outside the work root). Evidence = why, plus what would make it verifiable.

A fail is the useful outcome. Report it plainly and immediately; do not soften it, re-run it until it passes, or quietly fix the artifact and then report a pass — if you fix something, say that the first run failed and show both runs.

Step 4 — Report

**Check-work: FAIL**

- [PASS] `src/gideon/check_work.py` contains `derive_checks` — `grep -n 'derive_checks' src/gideon/check_work.py`
  - evidence: src/gideon/check_work.py:196: def derive_checks(claims, ...)
- [FAIL] `tests/test_check_work.py` exists — `test -e tests/test_check_work.py`
  - evidence: no such path (the turn claimed tests were added)
- [UNVERIFIABLE] `curl -s localhost:10000/api/config` — no gateway is running here
  - evidence: connection refused; start `make serve` first and re-run

Verdict rules: any fail → FAIL. No fail and at least one executed pass → PASS. Nothing executed → UNVERIFIABLE — an empty report is never a pass.

If fewer than two checks were derivable, say that in one line ("only one claim in this session was checkable: …") instead of padding the report.

Scope — light and immediate

This is the light half of verification: seconds, current session, the claims that were just made. It does not read a spec, walk a whole feature, or replay a run. That depth belongs to the deep QA companion (see references/qa-boundary.md); when a check-work run keeps failing or the user wants whole-feature assurance, hand off there rather than growing this skill into it.

Unattended SDLC loops run this same derivation automatically after a stage gate passes when loops.check_work_stages is on — same module, same rules, no self-report.

© Sidiora-Labs, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in runtime/gideon/extensions/skills/bundled/check-work of Sidiora-Labs/centra-gideon-agent.

  • SKILL.md
  • references/qa-boundary.md

Open the folder on GitHubat commit ca531ee

Compare with similar skills

Check Work next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Check Work compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Check Work this skillSidiora-Labs/centra-gideon-agent217—~1.3kAutomated safety check: PassApache-2.0
ScheduleTinyAGI/tinyagi3.6k—~1.4kAutomated safety check: PassMIT
Send User MessageTinyAGI/tinyagi3.6k—~829Automated safety check: PassMIT
Cron Opsczl9707/build-your-own-openclaw1.9k—~593Automated safety check: PassMIT
X Bookmarkssharbelxyz/x-bookmarks289—~2kAutomated safety check: NotesNone
Wp Wpcli And OpsAutomattic/agent-skills2112 repos~988Automated safety check: PassNone

Similar skills

  • Schedule

    TinyAGI/tinyagi

    Create, list, and delete scheduled tasks (recurring or one-time) that send messages to agents.

    3.6k GitHub stars~1.4k tokensUpdated 6 mo ago
    Productivity & AutomationAuto-check passed

  • Send User Message

    TinyAGI/tinyagi

    Send a proactive message to a paired user via their channel (Discord, Telegram, or WhatsApp).

    3.6k GitHub stars~829 tokensUpdated 6 mo ago
    Productivity & AutomationAuto-check passed

  • Cron Ops

    czl9707/build-your-own-openclaw

    Create, list, and delete scheduled cron jobs. An agent skill from czl9707/build-your-own-openclaw.

    1.9k GitHub stars~593 tokensUpdated 3 mo ago
    Productivity & AutomationAuto-check passed

  • X Bookmarks

    sharbelxyz/x-bookmarks

    Fetch, summarize, and manage X/Twitter bookmarks via bird CLI or X API v2.

    289 GitHub stars~2k tokensUpdated 7 mo ago
    Productivity & AutomationAuto-check: notes

  • Wp Wpcli And Ops

    Automattic/agent-skills

    A skill your agent uses when working with WP-CLI (wp) for WordPress operations: safe search-replace, db export/import, plugin/theme/user/content management, cron, cache flushing, multisite, and…

    211 GitHub starsUsed in 2 repos~988 tokens
    Productivity & AutomationAuto-check passed

  • Ohdear

    ohdearapp/ohdear-cli

    Manage Oh Dear website monitoring using the ohdear CLI. An agent skill from ohdearapp/ohdear-cli.

    141 GitHub stars~1.1k tokensUpdated 1 mo ago
    Productivity & AutomationAuto-check passed

More from Sidiora-Labs/centra-gideon-agent

All 24 skills in this repo

  • Artifacts

    Sidiora-Labs/centra-gideon-agent

    Persist, version, and iterate on LLM-generated UI (widgets, HTML, markdown).

    217 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Best Of N

    Sidiora-Labs/centra-gideon-agent

    Sample several candidate answers in parallel, judge them against stated criteria, and present the winner with the runners-up kept one click away.

    217 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Document Authoring

    Sidiora-Labs/centra-gideon-agent

    Author a real document — a report, proposal, slide deck, spec, or paper — by settling audience, claim, and structure before drafting prose, then writing to that structure.

    217 GitHub stars~970 tokensUpdated today
    Auto-check passed

  • Editorial Document

    Sidiora-Labs/centra-gideon-agent

    Write long-form editorial documents as clean, semantic HTML saved as an artifact (kind=document) — reports, briefs, explainers, proposals, write-ups.

    217 GitHub stars~1.3k tokensUpdated today
    Auto-check passed

  • Gideon API

    Sidiora-Labs/centra-gideon-agent

    The operator's manual for DRIVING Gideon's API and tools — how to find an exact tool/route signature, the mandatory verify-after-mutate loop, and what NOT to hand-roll.

    217 GitHub stars~1.4k tokensUpdated today
    Auto-check passed

  • Infographic Syntax

    Sidiora-Labs/centra-gideon-agent

    Author infographics with the AntV declarative DSL — pick a template, fill a small indented data tree, and save as an artifact (kind=infographic) that renders to crisp SVG and streams as you write it.

    217 GitHub stars~1.1k tokensUpdated today
    Auto-check passed

Categories

Questions about Check Work

What does Check Work do?

Verify what you just claimed, with real tool calls — reconstruct the claims from this session, derive 2-4 executable checks from those specific claims, run every one, and report pass/fail with…. Check Work is an agent skill from Sidiora-Labs/centra-gideon-agent. Verify what you just claimed, with real tool calls — reconstruct the claims from this session, derive 2-4 executable checks from those specific claims, run every one, and report pass/fail with quoted evidence.

When should I use Check Work?

Check Work fits situations like: tasks that involve Scheduled and recurring tasks.

How do I install Check Work in Claude Code?

Run `npx skills add Sidiora-Labs/centra-gideon-agent --skill check-work -a claude-code`. Or copy the skill folder (runtime/gideon/extensions/skills/bundled/check-work in Sidiora-Labs/centra-gideon-agent) into .claude/skills/check-work in your project. Claude Code loads it when a task matches its description.

How do I install Check Work in Codex?

Run `npx skills add Sidiora-Labs/centra-gideon-agent --skill check-work -a codex`. Or copy the skill folder (runtime/gideon/extensions/skills/bundled/check-work in Sidiora-Labs/centra-gideon-agent) into .agents/skills/check-work in your project. Codex loads it when a task matches its description.

Can I use Check Work in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Sidiora-Labs/centra-gideon-agent --skill check-work -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/check-work, .gemini/skills/check-work, .github/skills/check-work and .opencode/skills/check-work in your project.

What does Check Work need to run?

Going by SKILL.md and its folder, Check Work needs the command-line tools its instructions call (make, python and curl). Our summary lists: Python 3.

Does Check Work access the network?

SKILL.md contains no URLs. Its commands use curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Check Work safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Check Work use?

Check Work is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Check Work use?

About 1.3k tokens (SKILL.md is roughly 5.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 624 tokens, read only when the agent opens those files.

What are the alternatives to Check Work?

Skills that share tags, products or a category with Check Work: Schedule (TinyAGI/tinyagi, 3.6k stars), Send User Message (TinyAGI/tinyagi, 3.6k stars), Cron Ops (czl9707/build-your-own-openclaw, 1.9k stars) and X Bookmarks (sharbelxyz/x-bookmarks, 289 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Check Work?

Sidiora-Labs (a GitHub organization) maintains it in Sidiora-Labs/centra-gideon-agent, which has 217 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on October 8, 2026.

Source: Sidiora-Labs/centra-gideon-agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.