pathfinder
Skill2 starsChanged 8 months agoMITView on GitHub
The single entry point for all Pathfinder skills. Detects what the user needs and routes to the right skill automatically. Also provides shortcut modes — /learn, /build, /reflect, /share. Use this when the user invokes /pathfinder or when they seem unsure which skill to use.
10 other projects use a version of this.
Adopted by
Most recently taken up by
- MMACABRE/SKILLStheir own version, first seen Nov 8, 2026
- susantedit/claude-skillstheir own version, first seen Oct 20, 2026
- oivanfelipe/claude-skillstheir own version, first seen Oct 13, 2026
- Pasquale-Favella/watchtowertheir own version, first seen Oct 11, 2026
- dgilford/ai-science-toolkittheir own version, first seen Oct 1, 2026
- gcapodeferro02/my-agent-skillstheir own version, first seen Sep 21, 2026
Used with
Projects with it also use oh-my-issues, what-the and 8 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.
tuliosalustiano27Skilloh-my-issues
Cluster a GitHub issue backlog by root cause into a small set of plan-master issues, redirect children with a standardized comment, and bundle architectural-fix PRs that close clusters atomically. Use when an issue tracker has accumulated dozens of reports that share underlying defects, when asked to triage / consolidate / cluster / dedupe issues, when asked to build a plan series or roadmap from open issues, or when routing a new incoming bug into an existing plan.
Also in 3 projects that use this
tuliosalustiano27Skillwhat-the
What the? Use when the user wants a plain-English breakdown of something technical — the who, what, where, why, and when.
Also in 3 projects that use this
tunnckoCoreSkillhow-it-works
Use for 'how does X work', code walkthroughs before changing something, and placement / ownership / layering questions ('where should this live', 'which package owns this', 'is this the right layer'). Explains subsystem architecture, runtime flow, onboarding mental models. Can critique architecture. Use why for motivation.
Also in 4 projects that use this
magnusrodsethSkilllearn-codebase
Understand a codebase by reading its actual source, on GitHub or on disk: how a pattern is really implemented, an org's conventions, how two things are wired. Use for \"how does <repo> do X\". For published API docs prefer find-docs.
Also in 5 projects that use this
dqtx760Skilltimeline-report
Generate a "Journey Into [Project]" narrative report analyzing a project's entire development history from claude-mem's timeline. Use when asked for a timeline report, project history analysis, development journey, or full project report.
Also in 3 projects that use this
barrelcSkillmem-search
Search kimi-mneme's persistent cross-session memory database. Use when user asks "did we already solve this?", "how did we do X last time?", "what did we do yesterday?", or needs work from previous sessions.
Also in 4 projects that use this
Other versions10 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 10
- dgilford/ai-science-toolkit★ 82same name
- thedotmack/mackeroni-skills★ 16same name
- emaraschio/cursor-commands★ 9same name
- dqtx760/skills-manage★ 2same name
- gcapodeferro02/my-agent-skills★ 1same name
- MMACABRE/SKILLS★ 1same name
- Pasquale-Favella/watchtower★ 1same name
- tuliosalustiano27/Skills_Claude_Code★ 1same name
- oivanfelipe/claude-skills★ 0same name
- susantedit/claude-skills★ 0same name
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 repository18 other files it gives its agents.
- agent-architectSkill
- api-explorerSkill
- apps-script-builderSkill
- build-first-break-laterSkill
- buildSkill
- courage-modeSkill
- hypothesis-labSkill
- impact-mapperSkill
- iteration-journalSkill
- learnSkill
- lessonsSkill
- reflectSkill
- shareSkill
- show-your-workSkill
- teach-backSkill
- tech-translatorSkill
- unknown-unknownsSkill
- workflow-detectiveSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
15 rules. 0 are common, 15 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 10 edited versions we read keep these.
15
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 14
When activated, Pathfinder does ONE of three things:
- Distinctive: line 16
If the user said something specific, route to the right skill immediately
- Distinctive: line 17
If the user seems unsure, ask a simple question to figure out where they are
- Distinctive: line 18
If the user wants to browse, show the quick menu
- Distinctive: line 54
When the user seems unsure or asks "what can you do?", show this:
- Distinctive: line 103
When one skill naturally leads to another, suggest the transition:
- Distinctive: line 105
After workflow-detective finds an opportunity → "Ready to build?
- Distinctive: line 106
After build-first-break-later finishes v1 → "Want to capture what you learned?
- Distinctive: line 107
After iteration-journal entry → "Want to share this with your team?
- Distinctive: line 108
After show-your-work generates artifacts → "Want to teach someone else?
- Distinctive: line 109
After any build → "Want to measure the impact?
- Distinctive: line 110
After debugging/fixing something → "Want to save this as a lesson so others don't hit the same issue?
- Distinctive: line 111
After a lesson is created → "Want to share this with the team?
- Distinctive: line 115
When the user says "pathfinder status" or "where am I?", show:
- Distinctive: line 125
Only show the menu when genuinely unsure
“Common” is measured: kept by at least 6 in 10 of the 10 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
Overview
One skill to rule them all. Pathfinder listens to what you say and activates the right skill behind the scenes. You never need to remember 13 names — just talk naturally.
Keywords: pathfinder, help, what do I do, where do I start, guide, router, menu
How It Works
When activated, Pathfinder does ONE of three things:
- If the user said something specific, route to the right skill immediately
- If the user seems unsure, ask a simple question to figure out where they are
- If the user wants to browse, show the quick menu
Intent Detection
Map natural language to the right skill.
Emotional state signals:
- Fear/hesitation/overwhelm → courage-mode
- Confusion about technical terms → tech-translator
- Excitement about an idea → hypothesis-lab
- Frustration ("this isn't working") → tech-translator + courage-mode
Action signals:
- Wants to find what to build → workflow-detective
- Wants to start building → build-first-break-later
- Wants to build in Google Workspace → apps-script-builder
- Wants to connect systems → api-explorer
- Wants to build something smarter → agent-architect
- Wants to understand something → tech-translator
- Wants to reflect → iteration-journal
- Wants to share/present → show-your-work
- Wants to prove value → impact-mapper
- Wants to teach others → teach-back
- Wants to know what they're missing → unknown-unknowns
- Wants to document a discovery/quirk/workaround → lessons
Question signals:
- "Where do I start?" → Show the quick menu
- "What can you do?" → Show all available skills
- "What should I do next?" → Check iteration-journal for context, suggest next step
Quick Menu
When the user seems unsure or asks "what can you do?", show this:
What would you like to do?
🧭 LEARN — Understand technical things in plain English
🔨 BUILD — Create automations, scripts, apps, or agents
📓 REFLECT — Capture what you learned and track growth
📣 SHARE — Show others what you built and teach them
Or just tell me what's on your mind — I'll figure out the right tool.Shortcut Modes
/learn mode
Activates: tech-translator (always-on) + courage-mode + unknown-unknowns
Best for: exploring, understanding, getting comfortable
Tell the user: "Learning mode is on. Everything technical will be explained in plain English. If you get stuck, I've got you. And I'll point out interesting things you might not have thought to ask about."
/build mode
Activates: workflow-detective + hypothesis-lab + build-first-break-later + apps-script-builder + api-explorer + agent-architect
Best for: creating something new
Tell the user: "Build mode is on. I'll help you find what to build, form a hypothesis, get a rough version working fast, and level up from there. What do you want to create?"
/reflect mode
Activates: iteration-journal + impact-mapper
Best for: end of session, end of week, measuring progress
Tell the user: "Reflect mode is on. Let's capture what you built, what you learned, and measure the impact. Ready to journal?"
/share mode
Activates: show-your-work + teach-back
Best for: presenting, documenting, training others
Tell the user: "Share mode is on. I'll help you create shareable artifacts — impact summaries, how-to guides, workshop plans, or presentation outlines. What do you want to share?"
Smart Transitions
When one skill naturally leads to another, suggest the transition:
- After workflow-detective finds an opportunity → "Ready to build? Say 'let's build it'"
- After build-first-break-later finishes v1 → "Want to capture what you learned? Say 'journal'"
- After iteration-journal entry → "Want to share this with your team? Say 'show my work'"
- After show-your-work generates artifacts → "Want to teach someone else? Say 'help me teach this'"
- After any build → "Want to measure the impact? Say 'what's the impact?'"
- After debugging/fixing something → "Want to save this as a lesson so others don't hit the same issue? Say 'create a lesson'"
- After a lesson is created → "Want to share this with the team? Say 'show my work'"
Status Check
When the user says "pathfinder status" or "where am I?", show:
- Current active mode (learn/build/reflect/share or individual skill)
- What they've done this session
- Suggested next step
Tone Guidelines
- Concise and helpful — don't overwhelm with options
- Confident routing — when you know what they need, just go there, don't ask
- Only show the menu when genuinely unsure
- Smooth transitions between skills — make it feel like one continuous experience, not 13 separate tools
- "I've got the right tool for that — let me switch gears"
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.

