roadmap
Skill23 starsChanged 2 months agoMITView on GitHub
Use when work spans weeks and the reasoning behind it is piling up: returning to a project after time away, \"why did we decide X?\", \"where did we land on this?\", \"what's still open?\", onboarding someone onto a long-running build, or a choice everyone remembers making and nobody can find. Not one session's state (that's `handoff`), not scoping one feature (that's `interview`).
48 other projects use a version of this.
Adopted by
Most recently taken up by
- gopalparashar421/agent-skillstheir own version, first seen Nov 8, 2026
- dirien/yet-another-agent-harnesstheir own version, first seen Nov 8, 2026
- Ovich/charrettetheir own version, first seen Nov 7, 2026
- ryanmoelter/plumetheir own version, first seen Nov 4, 2026
- eyssette/js-templatetheir own version, first seen Nov 1, 2026
- danielcherubini/skillstheir own version, first seen Nov 1, 2026
Used with
Projects with it also use sequence, stakeholder-update and 7 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.
GTMifySkillsequence
Build a multi-channel outreach cadence (email + LinkedIn + phone) for a target persona or named prospect. Use when the user says 'build a sequence', 'outreach cadence', 'multi-touch sequence', 'multi-channel cadence', 'follow-up sequence', or needs a coordinated multi-channel play. Do NOT use for single cold emails — use cold-email instead.
Also in 3 projects that use this
AnthropicSkillstakeholder-update
Generate a stakeholder update tailored to audience and cadence. Use when writing a weekly or monthly status for leadership, announcing a launch, escalating a risk or blocker, or translating the same progress into exec-brief, engineering-detail, or customer-facing versions.
Also in 3 projects that use this
EpistatesSkillstrategy
Plan weekly or monthly X content strategy. Use when the user wants to plan their content calendar, set growth goals, build a content pipeline, or think strategically about their X presence.
Also in 3 projects that use this
GitHubSkillprd
Generate high-quality Product Requirements Documents (PRDs) for software systems and AI-powered features. Includes executive summaries, user stories, technical specifications, and risk analysis.
Also in 7 projects that use this
michalattSkillchallenge
Pressure-test plans, decisions, and directions by picking and answering the most relevant challenge questions for the current conversation
Also in 3 projects that use this
anombyte93Skilldiscover
Phase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery. Delegates to superpowers:brainstorming in Interactive Mode (one adaptive question at a time), or self-brainstorms in Autonomous Mode when no user is present. Intercepts before the brainstorming chain hands off to writing-plans — this skill owns the exit. Extracts constraints, calibrates scale (Solo / Team / Enterprise), and advances the pipeline to GENERATE.
Also in 4 projects that use this
Other versions48 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 48
- cloudposse/atmos★ 1.4ksame name
- me2resh/apexyard★ 542same name
- andreaskelm/pm-brain★ 235same name
- genkovich/sdd★ 187same name
- YougLin-dev/Aha-Loop★ 181same name
- Ovid/paad★ 150same name
- facebookresearch/autoform-bot★ 136same name
- Mehdibargach/claude-code-pm-skills★ 97same name
- joshuadavidthomas/agent-skills★ 49same name
- spmtitsolution/OpenBA-Kit★ 38same name
38 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 repository34 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- analyzeSkill
- assessSkill
- blueprintSkill
- breakdownSkill
- buildSkill
- checklistSkill
- clarifySkill
- constitutionSkill
- convergeSkill
- debugSkill
- deepenSkill
- deprecateSkill
- double-checkSkill
- explainSkill
- handoffSkill
- helpSkill
- initSkill
- interviewSkill
- learnSkill
- levelupSkill
- lintSkill
- living-docsSkill
- performanceSkill
- personaSkill
- promptSkill
- prototypeSkill
- qaSkill
- quarantineSkill
- reportSkill
- routeSkill
- signatureSkill
- specifySkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 41 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 41
Write the fog as one line naming the unknown and what will lift it: *"Billing model, unspecified until the pilot returns pricing …
“Common” is measured: kept by at least 6 in 10 of the 41 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
MasterMind: Roadmap
Long work loses its reasoning long before it loses its code. Six sessions in, the why behind a choice is gone, and the seventh session relitigates it, or silently undoes it. This is the one artifact that outlives the sessions: a decision map the project owns and appends to for the life of the work.
The file: five sections
.mastermind/MAP.md, one per project. Nothing that isn't one of these five belongs in it.
- Destination: what done looks like, in two or three lines. What every decision is measured against.
- Decisions so far: dated, one line each, each with its why. Append-only.
- Open questions: what you can state precisely and cannot answer yet.
- Not yet specified: known unknowns, deliberately unplanned.
- Out of scope: and what it would take to change that.
A decision entry, and the reversal of one, look like this:
2026-03-04 · Sessions live in Postgres, not Redis: one datastore to operate, and
nothing needed sub-millisecond reads. → specs/auth.md
2026-05-19 · REVERSES 2026-03-04: sessions move to Redis. The read path became the
p99 at 340ms once org switching landed. The original reason still held;
the traffic changed. → PR #412Only section 2 is append-only. The other four describe the present and get rewritten freely: a resolved question leaves "Open questions" the moment it becomes a decision.
Fog of war: don't chart what you can't see
The test for "Open questions" is whether you can state the question precisely today, not whether you can answer it. "Which queue runs the nightly export?" is an open question. "How does billing work?" isn't a question yet; it's a region of fog.
Write the fog as one line naming the unknown and what will lift it: "Billing model, unspecified until the pilot returns pricing feedback." That line is the whole entry. A map carrying a plausible plan for month three reads as decided, and the next session builds against something nobody ever chose.
Decisions are append-only
Never edit or delete a decision entry. A reversal is a new dated entry naming the one it reverses and what changed. The excuse to catch in yourself: "the old line is wrong now, so leaving it is misleading." It was true when it was written, and when it stopped being true is the information, the map exists to answer "why is it like this?" nine months later, and an edited history cannot.
An index, not a store
Each entry is one line plus a pointer: to the spec, the PR, the file, the issue. Detail stays where
it already lives and stays current there. A map that reproduces content becomes a second source of
truth, and the copy is the one that goes stale (~/.mastermind/engineering/core/rigor.md refuse-list).
One open question per session
Resolve one open question per session. A session that closes five has been guessing at four. A question leaves "Open" only when something outside the map settled it: a measurement, a call from the user, code that now exists: and the entry that replaces it says which.
When it gets written
In a project that works from specs/, converge hands this map the decisions a converged feature
leaves behind, one line each with a pointer to the frozen feature folder.
An entry is earned at the same moment the journal line is: the verdict closing a non-trivial task
(~/.mastermind/engineering/core/rigor.md). The journal records what happened; the map carries only
the decisions still shaping the work. Promote from the journal, never copy it across.
Map vs. handoff vs. spec
Three horizons, and the boundary is what each one outlives.
interview: one ask, decided before it's built. Retired when that thing ships.handoff: one session's live state, so a reset doesn't cost the thread. Thrown away on resume.roadmap: the project's decision history, kept for the project's life. It points at specs and handoffs; it never absorbs them.
Gotchas
- Open it before planning, not after. Coming back cold, the reflex is to re-derive the state from the code: which reads the what and misses every why, and reopens settled ground.
- Out-of-scope work never quietly graduates back in. Scope discipline is
rigor.md; the part that's the map's job is that moving an item out of "Out of scope" is itself a dated decision entry: who asked, and why now. - Write it for someone who wasn't there. A line that only makes sense to whoever was in the session fails at the two moments the map is for: the return after weeks away, and the new person.
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.

