todo
Skill1 starsChanged 8 days agoMITView on GitHub
Manage local .todo lists for bugs, ideas, features, and tasks. When explicitly asked to manage project progress, queues, or project chiefs, use the included references/project-management.md along with the projectbot skill if needed.
37 other projects use a version of this.
Adopted by
Most recently taken up by
- thistleknot/skillstheir own version, first seen Nov 8, 2026
- uwuclxdy/agenticattheir own version, first seen Nov 8, 2026
- PatrickSUDO/fadacai-portfoliotheir own version, first seen Nov 6, 2026
- rodeyseijkens/skillstheir own version, first seen Nov 6, 2026
- NazmusSayad/skillstheir own version, first seen Nov 1, 2026
- DegreeSign/skillstheir own version, first seen Nov 1, 2026
Used with
Projects with it also use standup, update-docs and 10 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.
AnthropicSkillstandup
Generate a standup update from recent activity. Use when preparing for daily standup, summarizing yesterday's commits and PRs and ticket moves, formatting work into yesterday/today/blockers, or structuring a few rough notes into a shareable update.
Also in 3 projects that use this
Hugging FaceSkillupdate-docs
Update documentation across the repo after API changes. Finds stale references in docs, examples, docstrings, and fixes them.
Also in 3 projects that use this
sunnyclinches44Skillexplain
Explains code using real-world analogies and ASCII diagrams
Also in 3 projects that use this
Hugging FaceSkillimplement
Make tests pass. Invoke after /write-tests produces failing tests.
Also in 5 projects that use this
Google CloudSkilltriage
Gather context on a change or bug and plan the implementation.
Also in 4 projects that use this
photon-groveSkillunslop
Detects and rewrites generic, overly polished, or AI-sounding prose while preserving meaning. Use when the user asks to "unslop", humanize, de-AI, tighten, or review whether writing sounds generated.
Also in 3 projects that use this
Other versions37 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 37
- vladmandic/sdnext★ 7.4ksame name
- PatrickSUDO/fadacai-portfolio★ 145same name
- ronaknnathani/relay★ 43same name
- freemty/labmate★ 25same name
- ceptln/quota-burner★ 18same name
- thaitype/skills★ 13same name
- eranw2000/multi-phase-skills-framework★ 10same name
- rbrown101010/Rileys-Top-Skills★ 9same name
- uwuclxdy/agenticat★ 7same name
- fedemelo/agent-config★ 4same name
27 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 repository23 other files it gives its agents.
- AGENTS.mdAGENTS.md
- aftermath-rewindSkill
- aiconographerSkill
- ask-socratesSkill
- check-project-nameSkill
- goal-checkSkill
- lean-proof-reviewSkill
- parallax-imageSkill
- prior-artSkill
- projectbotSkill
- quiet-uxSkill
- rmddSkill
- rmdsSkill
- rmdvSkill
- rrr-review-remedy-respondSkill
- soft-skill-creatorSkill
- thought-rigSkill
- verifier-systemSkill
- what-huhSkill
- what-whatSkill
- write-humanlySkill
- write-plainlySkill
- write-simplified-technical-englishSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
27 rules. 0 are common, 20 are distinctive, and 7 are very specific to this project.
0
Common
Most of the 34 edited versions we read keep these.
20
Distinctive
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Use this skill whenever the user asks to track, triage, clean up, summarize, search, or resolve entries in local TODO files.
- Distinctive: line 23
Use the root lists unless a subproject is named.
- Distinctive: line 36
Do not create files unless explicitly needed by the user command.
- Very specific: line 37
If .todo/ does not exist, create it only when a command needs it.
- Very specific: line 38
Search the intended .todo/ files explicitly.
- Distinctive: line 57
Use this format for all managed files.
- Distinctive: line 62
Keep concrete details, examples, error text, reproduction notes, uncertainty, urgency, and tone unless they contain secrets or unrelated …
- Distinctive: line 63
Prefer appending brief metadata around the user's text over rewriting the item.
- Distinctive: line 64
If cleanup is needed for readability, keep the original meaning and details intact.
- Distinctive: line 65
When adding a completion note, leave the original item text recognizable and add the resolution after it.
- Distinctive: line 70
Remove punctuation around type.
- Very specific: line 80
Create .todo/<type>.md if missing, with both sections.
- Distinctive: line 83
Only normalize whitespace and markdown-breaking characters when needed.
- Distinctive: line 93
When the human asks this chat to do an item, check for existing work, record this chat's assignment, and proceed.
- Distinctive: line 98
If no open items exist, report that the list is already clear.
- Distinctive: line 99
Treat popping an item as accepting the work now, not just removing it from the list.
- Distinctive: line 100
Read and follow the current project's instructions before implementing, including AGENTS.md and any referenced project docs.
- Distinctive: line 106
If context is not enough, ask for confirmation before marking complete.
- Distinctive: line 107
If confirmation is available in the user message, close it directly with a short resolution note.
- Very specific: line 115
Search all markdown files in .todo/ for the query.
- Very specific: line 126
Default to all unless a specific type is requested.
- Distinctive: line 148
Keep output compact and scannable.
- Distinctive: line 152
If the user says something like "pop bugs" or "pop one item", default to the same top-item flow above for the inferred list.
- Distinctive: line 157
If the user says "update the todo" without a clear type, ask for the list type first unless context already implies one.
- Very specific: line 161
Always use ISO date format YYYY-MM-DD for completion entries.
- Distinctive: line 162
When adding completion notes for bugs, include what was changed or observed.
- Very specific: line 167
Add .todo/ to .gitignore in the project if not already present.
“Common” is measured: kept by at least 6 in 10 of the 34 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
Todo
This skill manages local, project-specific task tracking in markdown files under the repository root .todo/ directory.
Use this skill whenever the user asks to track, triage, clean up, summarize, search, or resolve entries in local TODO files.
Todo works independently. Use Projectbot when the human wants a project chief; ordinary Todo work needs no chief or worker setup.
Project-management requests
For coordinated work, read the project records reference.
Also read it and the relevant brief when .todo/projects/PROJECT.md already exists
or an assignment supplies a control directory. Respect current assignments,
lifecycle, and other chats' edits before changing lists. The records can be used
without Projectbot; installation alone doesn't assign a chief.
Use the root lists unless a subproject is named. For a subproject, the list paths below refer to its own directory.
Scope and storage
- Ordinary list files live under the current project root in
.todo/<type>.md. Managed subprojects use the locations defined by the extension. - Supported types:
bugs.mdideas.mdfeatures.mdtasks.md
- Any other user-defined type maps to
<normalized type>.mdin.todo/(for example:todo chore->.todo/chore.md). - Do not create files unless explicitly needed by the user command.
- If
.todo/does not exist, create it only when a command needs it. - Search the intended
.todo/files explicitly; avoid unrelated hidden paths. List maintenance changes tracking files only.popalso authorizes the selected implementation work under the project's normal instructions.
Canonical list format
Each tracked file should have these sections:
## Open## Completed
Open item:
[ ] <item text>
Completed item:
[x] <item text> - resolved: <resolution note> (YYYY-MM-DD)
Use this format for all managed files.
Preserve user wording
- Preserve the user's original wording as closely as practical when adding or moving items.
- Keep concrete details, examples, error text, reproduction notes, uncertainty, urgency, and tone unless they contain secrets or unrelated noise.
- Prefer appending brief metadata around the user's text over rewriting the item.
- If cleanup is needed for readability, keep the original meaning and details intact.
- When adding a completion note, leave the original item text recognizable and add the resolution after it.
Type normalization
- Normalize type tokens to lowercase.
- Remove punctuation around type.
- Convert spaces to hyphens.
bug->bugs,idea->ideas,feature->features,task->tasks, plural inputs are accepted as-is.- Unknown types are treated as first-class custom files using normalized names.
Commands
push <type> <description>
- Determine the target list file from
<type>. - Create
.todo/<type>.mdif missing, with both sections. - Append one unchecked bullet under
## Open. - Preserve
<description>closely, including tone and useful detail. - Only normalize whitespace and markdown-breaking characters when needed.
pop <type>
- Determine the target list file from
<type>. - Take the top unchecked item in
## Open. - For managed items, take the first eligible queued item in list order. Skip assigned, blocked, paused, or cancelled items and items with unmet dependencies. Preserve their IDs and metadata. A request to pop does not silently resume a sleeping or cancelled project; explain its state if there is no eligible work.
- When the human asks this chat to do an item, check for existing work, record this chat's assignment, and proceed. An assigned chief does not require a handoff, permission request, or message to that chief. Reread before updating shared records; resolve actual conflicting assignments rather than assuming a conflict merely because another chat can edit them.
- If no open items exist, report that the list is already clear.
- Treat popping an item as accepting the work now, not just removing it from the list.
- Read and follow the current project's instructions before implementing, including AGENTS.md and any referenced project docs.
- Validate that the item still applies before doing the work. For bugs, verify the issue when possible; if context is not enough, ask for confirmation before changing code or marking complete.
- Implement the popped item professionally using the project's normal engineering guidelines, tests, documentation, and review expectations.
- Move the selected item to
## Completedonly after the work is implemented or conclusively determined to be obsolete. - Preserve the original item text when moving it.
- For
bugs/bug, validate if it is still an issue before closing:- If context is not enough, ask for confirmation before marking complete.
- If confirmation is available in the user message, close it directly with a short resolution note.
- For other types, prefer immediate resolution unless the user explicitly asks for confirmation.
- Completed note should be short and specific:
resolved: implemented <specific work> (YYYY-MM-DD)resolved: obsolete after verification <specific reason> (YYYY-MM-DD)
search todo <query>
- Search all markdown files in
.todo/for the query. - In ordinary mode, search direct list files only. Project-management searches can include subproject lists, excluding project records from item counts.
- Return grouped results with:
- file
- section (Open/Completed)
- line text
- Match should be case-insensitive and include partial phrase matches.
analyze todo [type|all]
- Default to
allunless a specific type is requested. - Report for each relevant file:
- total items
- open count
- completed count
- completion percentage
- Label percentages as list-item completion, not overall project progress. For managed lists, report cancelled items separately and exclude them from the completion denominator.
- Flag files with:
- no file
- missing sections
- no open items
- Offer concise follow-up suggestions (e.g. next candidate to pop, stale backlog, etc.).
summarize todo [type|all]
- Default to
allunless a specific type is requested. - Return:
- top open items per list (up to 5 each)
- number of completed items this session
- quick next-step recommendations
- Keep output compact and scannable.
Pop behavior for mention-style requests
If the user says something like "pop bugs" or "pop one item", default to the same top-item flow above for the inferred list. Begin work on the popped item immediately, then mark it completed after the implementation or verification outcome is finished.
Ambiguous mentions
If the user says "update the todo" without a clear type, ask for the list type first unless context already implies one.
Completion date and notes
Always use ISO date format YYYY-MM-DD for completion entries.
When adding completion notes for bugs, include what was changed or observed.
File policy
.todo/and files inside it are local and should remain out of version control.- Add
.todo/to.gitignorein the project if not already present.
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.

