chief-of-staff
Skill0 starsChanged todayMITView on GitHub
Pursue a long-running goal in a single session by co-ordinating subagents.
40 other projects use a version of this, 12 of them edited; 7 of 11 edited versions we compared changed its rules.
How people change it
7 of 11 edited versions changed its rules.
Of the 11 edited versions we compared: 4 are an older text, 7 made changes of their own.
Not in older versions
- Ingest. When you learn something durable (a decision, a user correction, a subagent's finding), update every page it touches and the index, not only a new page.missing from 4 of 4
- Query. Before a decision, read
index.mdand the pages it points to. If the answer you build is worth keeping, file it as a page.missing from 4 of 4 - When a claim concerns code, cite the commit it was true at, with its repo: "As of
mattpocock/skills@abc1234,retroloadswriting-for-agentsin step 1."missing from 4 of 4 - Never write "currently", "now" or "is" about code without a date or commit beside it.missing from 4 of 4
- When something changes, add a new dated claim and mark the old one superseded. Don't rewrite the old one.missing from 4 of 4
- 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.missing from 4 of 4
Rules people drop
- 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.dropped by 6 of 7 - Ingest. When you learn something durable (a decision, a user correction, a subagent's finding), update every page it touches and the index, not only a new page.dropped by 5 of 7
- When a claim concerns code, cite the commit it was true at, with its repo: "As of
mattpocock/skills@abc1234,retroloadswriting-for-agentsin step 1."dropped by 5 of 7 - Never write "currently", "now" or "is" about code without a date or commit beside it.dropped by 5 of 7
- When something changes, add a new dated claim and mark the old one superseded. Don't rewrite the old one.dropped by 5 of 7
- Query. Before a decision, read
index.mdand the pages it points to. If the answer you build is worth keeping, file it as a page.dropped by 4 of 7 - All work should be done in subagents. Protect your context window.dropped by 1 of 7
- Use background agents so you can stay in active dialogue with the user. Start every subagent with a fresh context window.dropped by 1 of 7
We split this file and each edited version into the rules they give an agent and match them by wording. A version that adds no rule of its own and has not changed since this file last did reads as an older text, so what it lacks is not counted as dropped. We keep no past texts of a file, so that is inferred, and an edited version that started from an older text still counts its gaps as drops.
Adopted by
Steady: 0 new projects took it in the last 4 weeks, none the 4 weeks before.thin data
Most recently taken up by
- devdeepjs/kobayashi-maruedited, first seen Nov 16, 2026
- trajectonomics/skillsword for word, first seen Nov 15, 2026
- geoffbremner/skillsword for word, first seen Nov 15, 2026
- HiteSit/real-scientist-skillsword for word, first seen Nov 15, 2026
- QiYueran-source/waymarkword for word, first seen Nov 15, 2026
- peterpme/skillstheir own version, first seen Nov 8, 2026
Other versions40 projects use a version of this.
Word for word · 6
- mattpocock/skills★ 325k100% same
- QiYueran-source/waymark★ 112100% same
- HiteSit/real-scientist-skills★ 27100% same
- geoffbremner/skills★ 4100% same
- op3616windows/skills★ 1100% same
- trajectonomics/skills★ 1100% same
Edited · 12
- caterpi11ar/giclaw★ 996% same
- devdeepjs/kobayashi-maru★ 297% same
- fabiandistler/agents★ 296% same
- IsKenKenYa/skills★ 294% same
- christofferbergj/agent-skills★ 161% same
- vincenzo345/skills★ 196% same
- ZeroTokenClaw/agents-skills★ 196% same
- 5thlayer/skillworks★ 097% same
- bradcstevens/git-loopy-skills★ 087% same
- kitloomlk-stack/agent-skill-builder-kit★ 096% same
2 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 repository72 other files it gives its agents.
- animate-expoSkill
- animateSkill
- animation-performanceSkill
- animation-vocabularySkill
- apple-designSkill
- ask-emilSkill
- ask-mattSkill
- ask-sonnerSkill
- better-typographySkill
- break-uiSkill
- choreographSkill
- claritySkill
- claude-handoffSkill
- codebase-designSkill
- code-reviewSkill
- cold-emailSkill
- content-strategySkill
- copywritingSkill
- croSkill
- diagnosing-bugsSkill
- domain-modelingSkill
- emil-design-engSkill
- find-animation-opportunitiesSkill
- frontend-designSkill
- gesturesSkill
- git-guardrails-claude-codeSkill
- grillingSkill
- grill-meSkill
- grill-with-docsSkill
- handoffSkill
- implementSkill
- implement-specSkill
- improve-animationsSkill
- improve-codebase-architectureSkill
- learn-tasteSkill
- loop-meSkill
- marketing-psychologySkill
- migrate-to-shoehornSkill
- mobile-nativeSkill
- persuasionSkill
- pick-ui-librarySkill
- prisma-client-apiSkill
- programmatic-seoSkill
- prototypeSkill
- prototype-variantsSkill
- prSkill
- remove-animationsSkill
- researchSkill
- retroSkill
- review-animationsSkill
- scaffold-exercisesSkill
- seo-auditSkill
- setup-matt-pocock-skillsSkill
- setup-pre-commitSkill
- setup-ts-deep-modulesSkill
- Skillpack Self-testSkill
- software-factorySkill
- supabase-postgres-best-practicesSkill
- tddSkill
- teachSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
9 rules. 0 are common, 6 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 31 edited versions we read keep these.
6
Distinctive
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
- Distinctive: line 20
All work should be done in subagents.
- Distinctive: line 22
Use background agents so you can stay in active dialogue with the user.
- Distinctive: line 36
Ingest: When you learn something durable (a decision, a user correction, a subagent's finding), update every page it touches and the index, …
- Very specific: line 37
Query: Before a decision, read index.md and the pages it points to.
- Very specific: line 45
When a claim concerns code, cite the commit it was true at, with its repo: "As of mattpocock/skills@abc1234, retro loads writing-for-agents …
- Distinctive: line 46
Never write "currently", "now" or "is" about code without a date or commit beside it.
- Distinctive: line 47
When something changes, add a new dated claim and mark the old one superseded.
- Very specific: line 54
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 72
No one-off workarounds, or hacks that bypass established processes
“Common” is measured: kept by at least 6 in 10 of the 31 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
All work should be done in subagents. Protect your context window.
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
Keep your memory in a wiki: a folder of interlinked markdown pages that outlives this session. Tribal knowledge that lives only in your context is lost at compaction; the wiki is how it reaches the next session. Look for a shared wiki first, one the user or other agents already keep, 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.
index.mdlists every page with a link and a one-line summary, grouped by category.- Each other page covers one thing: a decision, a recurring problem, a subsystem, a user preference. Link related pages to each other.
- Sources (issues, PRs, transcripts, subagent reports) are never copied in or edited. Pages cite them.
Three operations keep it alive:
- Ingest. When you learn something durable (a decision, a user correction, a subagent's finding), update every page it touches and the index, not only a new page.
- Query. Before a decision, read
index.mdand the pages it points to. If the answer you build is worth keeping, file it as a page. - Lint. Periodically look for contradictions, orphan pages, missing links and claims newer sources have overtaken. Suggest this as a schedule.
Write history, not the present
The wiki is a historical record. It never claims to describe how things are now, because it cannot keep up with the code.
- Date every claim: "On 2026-10-13, Matt decided..."
- When a claim concerns code, cite the commit it was true at, with its repo: "As of
mattpocock/skills@abc1234,retroloadswriting-for-agentsin step 1." - Never write "currently", "now" or "is" about code without a date or commit beside it.
- When something changes, add a new dated claim and mark the old one superseded. Don't rewrite the old one.
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
Be relentless in improving the environment. Use every user message as an excuse to search for these improvements.
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.

