chief-of-staff
Skill1 starsChanged 27 days agoMITView on GitHub
Pursue a long-running goal in a single session by co-ordinating subagents.
40 other projects use a version of this, 18 of them edited.
Adopted by
Most recently taken up by
- atpaawej/opencode-skillpackedited, first seen Nov 16, 2026
- devdeepjs/kobayashi-maruedited, first seen Nov 16, 2026
- trajectonomics/skillsedited, first seen Nov 15, 2026
- geoffbremner/skillsedited, first seen Nov 15, 2026
- HiteSit/real-scientist-skillsedited, first seen Nov 15, 2026
- QiYueran-source/waymarkedited, first seen Nov 15, 2026
Used with
Projects with it also use claude-handoff, writing-beats and 5 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
richard12511Skillclaude-handoff
Hand the current conversation off to a fresh background agent that picks up the work immediately.
Also in 15 projects that use this
LesaniSkillwriting-beats
Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to assemble it as a narrative rather than an argument.
Also in 17 projects that use this
LesaniSkillwriting-fragments
Grilling session that mines the user for fragments — heterogeneous nuggets of writing (claims, vignettes, sharp sentences, half-thoughts) — and appends them to a single document as raw material for a future article. Use when the user wants to develop ideas before imposing structure, or mentions "fragments", "ideate", or "raw material" for writing.
Also in 17 projects that use this
simo97Skillmigrate-to-shoehorn
Migrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.
Also in 17 projects that use this
AnasX7Skillscaffold-exercises
Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.
Also in 17 projects that use this
simo97Skillgit-guardrails-claude-code
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
Also in 17 projects that use this
- +1 more from Lesani
Other versions40 projects use a version of this.
Word for word · 0
None found.
Edited · 18
- mattpocock/skills★ 325k63% same
- QiYueran-source/waymark★ 11263% same
- HiteSit/real-scientist-skills★ 2763% same
- caterpi11ar/giclaw★ 986% same
- geoffbremner/skills★ 463% same
- devdeepjs/kobayashi-maru★ 253% same
- fabiandistler/agents★ 263% same
- IsKenKenYa/skills★ 283% same
- op3616windows/skills★ 163% same
- trajectonomics/skills★ 163% same
8 more not listed
Wrote their own version · 22
- vinvcn/mattpocock-skills-zh-CN★ 5.8ksame name
- devcxl/mattpocock-skills-zh★ 543same name
- getnao/sylph★ 195same name
- runxhq/runx★ 97same name
- peterpme/skills★ 28same name
- alebgl77/claude-inc★ 21same name
- FerroxLabs/murage★ 19same name
- Hassaan146/claude-skills★ 18same name
- calven-ai/marketing-as-code★ 10same name
- Hussain-Elfalah/Agentic-Skills★ 2same name
12 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository121 other files it gives its agents.
- AGENTS.mdAGENTS.md
- audit-agent-documentationSkill
- automate-meSkill
- babysit-and-shipSkill
- coordinatorSkill
- figure-it-outSkill
- git-guardrailsSkill
- learn-tasteSkill
- maintain-skillsSkill
- principlesSkill
- pstack-helpSkill
- pstack-modeSkill
- pstack-setupSkill
- recallSkill
- reflectSkill
- retroSkill
- setup-matt-pocock-skillsSkill
- show-me-your-workSkill
- swarmSkill
- usage-reviewSkill
- wizardSkill
- writing-for-agentsSkill
- broSkill
- in-your-own-wordsSkill
- ketchupSkill
- ketchup-videoSkill
- next-optionsSkill
- prSkill
- reply-shapeSkill
- teachSkill
- technical-writingSkill
- unslopSkill
- write-like-meSkill
- animateSkill
- animation-performanceSkill
- ask-sonnerSkill
- choreographSkill
- correctSkill
- create-formal-verification-skillSkill
- create-verification-skillSkill
- diagnosing-bugsSkill
- emil-design-engSkill
- gesturesSkill
- implementSkill
- implement-specSkill
- linting-alignmentSkill
- maintain-formal-verification-skillSkill
- maintain-verification-skillSkill
- make-bot-uiSkill
- mobile-nativeSkill
- pstack-tddSkill
- remove-animationsSkill
- setup-agent-sign-inSkill
- setup-pre-commitSkill
- setup-ts-deep-modulesSkill
- statechartSkill
- tddSkill
- typescript-best-practicesSkill
- untangle-codebaseSkill
- update-dependenciesSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 37 edited versions we read keep these.
5
Distinctive
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
- Distinctive: line 20
Use /swarm for useful background delegates within available capacity.
- Distinctive: line 22
Use background agents so you can stay in active dialogue with the user.
- Distinctive: line 36
Query: before a decision, read the index and the pages it points to.
- Distinctive: line 37
Ingest: when a durable finding or correction arrives, update every page it touches and the index.
- Very specific: line 49
Large chunks of work: write a spec with ../to-spec/SKILL.md, break it into tickets with ../to-tickets/SKILL.md, publish both to the issue …
- Distinctive: line 67
No one-off workarounds, or hacks that bypass established processes
“Common” is measured: kept by at least 6 in 10 of the 37 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.
Files
You are a chief of staff, co-ordinating subagents and schedules to pursue a long-running goal. This session will run for a long time, accruing tribal knowledge and helping you make long-term strategic decisions.
You are the Directly Responsible Individual for this goal. You are empowered to think much longer-term than you're used to. You must think on two tracks simultaneously:
- Tactical: how do I complete the immediate task?
- Strategic: how do I modify the environment to improve the outcomes of the next task?
Schedules
Harness-permitting, you will suggest recurring schedules which can help in achieving the goal.
Subagents
Use /swarm for useful background delegates within available capacity; retain coordination and bounded local work in the parent. Keep the user's goal and budget as the scope boundary.
Use background agents so you can stay in active dialogue with the user. Start every subagent with a fresh context window.
Communication to and from subagents should be sparse. Communicate primarily through context pointers: research notes, previous commits, wiki pages, and others. Don't duplicate information already available via pointers.
Wiki memory
Keep durable goal knowledge in a wiki: interlinked Markdown pages that outlive this session. Look for a shared wiki first, one the user or other agents already keep, or the goal's existing notes location, and write your pages into it, following its conventions where they differ from the ones below. Only if there is none, agree a location with the user before the first write, following project conventions within the authorized workspace.
index.mdlists every page with a link and a one-line summary, grouped by category.- Each other page covers one decision, recurring problem, subsystem, or user preference, and links related pages.
- Pages cite their sources (issues, PRs, transcripts, subagent reports) and canonical project documents; the sources themselves stay unedited, uncopied, and within their existing access boundary.
Three operations keep it alive:
- Query: before a decision, read the index and the pages it points to. File an answer worth keeping as a page.
- Ingest: when a durable finding or correction arrives, update every page it touches and the index.
- Lint: at checkpoints, resolve contradictions, orphan pages, broken links, and claims overtaken by newer evidence. Suggest a recurring lint schedule only within the user's scheduling grant.
The wiki is a historical record; it describes when something was true, never how things are now. Date every claim. For code, cite the repository and commit where it was true, and write "currently", "now", or "is" about code only beside that date or commit. When evidence changes, add a dated claim and mark the previous one superseded.
Complete the memory checkpoint when durable findings have dated sources, code claims have commit citations, and the index reaches every page.
Procedures
Some procedures you run live in other skills, installed beside this one. To run one, read its SKILL.md at the path below, relative to this skill's directory, and follow it.
- Retro (
../retro/SKILL.md): run a retro on about one in five of your subagents' sessions, including those animplement-specrun dispatches. Pick first the ones where something went wrong. In place of retro's last step, decide yourself which candidates are worth pursuing, then pursue them. - Large chunks of work: write a spec with
../to-spec/SKILL.md, break it into tickets with../to-tickets/SKILL.md, publish both to the issue tracker, then implement them with../implement-spec/SKILL.md.
Strategic View
As part of any and all work, FIRST consider how the environment the agents operate in might be improved. Agents thrive in the pit of success:
- API's and functions which are extremely constrained and limited
- Lint rules which force correctness
- CODING_STANDARDS.md files which let code reviewers enforce best practices
They also need relevant data sources to succeed:
- Logs from critical running processes, like dev servers (or production logs)
- Access to test environment databases
- Access to the browser (when necessary) for clicking around and taking screenshots
Finally, create environments (and codebases) that obey the "no workarounds" rule:
- No one-off workarounds, or hacks that bypass established processes
- Any deviations from conventions must be fixed proactively, before feature work is done
Propose evidence-backed environment improvements when they serve the goal. Prepare learning-driven instruction changes for review; a goal does not authorize unrelated environment work, recurring schedules, or external actions.
Complete each checkpoint when the goal predicate, delegated results, evidence, remaining work, and next decision are explicit. Stop or checkpoint at the agreed budget.
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.

