roadmap
Skill24 starsChanged 19 days agoMITView on GitHub
View your learning progress and recommended next steps
50 other projects use a version of this.
Adopted by
Most recently taken up by
- lengrufeng2008/dsh-skill-librarytheir own version, first seen Nov 15, 2026
- GravionLabs/skillstheir own version, first seen Nov 15, 2026
- Palatine-Labs/conisotheir own version, first seen Nov 15, 2026
- iuliandita/skillstheir own version, first seen Nov 15, 2026
- yarikleto/claude-teacher-plugintheir own version, first seen Nov 14, 2026
- facebookresearch/autoform-bottheir own version, first seen Nov 12, 2026
Used with
Projects with it also use sequence, stakeholder-update 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.
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
ArvorCoSkillspecify
Create feature specification from natural language description. Use when starting a new feature or creating a spec. Triggers on: create spec, specify feature, new feature spec.
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
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 versions50 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 50
- 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★ 154same name
- facebookresearch/autoform-bot★ 143same name
- Mehdibargach/claude-code-pm-skills★ 97same name
- joshuadavidthomas/agent-skills★ 49same name
- spmtitsolution/OpenBA-Kit★ 38same name
40 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
- CLAUDE.mdCLAUDE.md
- architectureSkill
- audit-contentSkill
- benchmarkSkill
- break-itSkill
- buildSkill
- challengeSkill
- code-reviewSkill
- compareSkill
- debug-ragSkill
- evaluateSkill
- explainSkill
- fixSkill
- glossarySkill
- journalSkill
- lessonSkill
- paper-reviewSkill
- quizSkill
- recapSkill
- sandboxSkill
- startSkill
- triageSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
25 rules. 0 are common, 20 are distinctive, and 5 are very specific to this project.
0
Common
Most of the 43 edited versions we read keep these.
20
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Read the learner's progress data and present a clear picture of where they are, what they have accomplished, and what to do next.
- Very specific: line 12
Read the following files from the progress/ directory:
- Very specific: line 20
If progress/learner-profile.md does not exist, the learner has not started yet.
- Distinctive: line 46
When a module is complete, show a badge next to it:
- Distinctive: line 74
Use visual progress bars built from ASCII characters.
- Very specific: line 78
Read .claude/docs/reference/milestones.md to load the milestone definitions.
- Distinctive: line 89
Use ✓ for complete, ◐ for in-progress (show fraction), ○ for not started.
- Distinctive: line 110
When a learner earns a new level, celebrate it prominently: "Congratulations — you've earned the RAG Practitioner level!
- Distinctive: line 114
Call out what the learner has accomplished:
- Distinctive: line 126
If there are notable achievements, celebrate them: "You have completed all beginner challenges — that is a solid foundation."
- Distinctive: line 145
Continue your current module: If a module is in progress, suggest the next lesson.
- Very specific: line 146
Fill a knowledge gap: If quiz results show a weak area, suggest /explain or /lesson for that topic.
- Distinctive: line 147
Take a challenge: If they have completed several lessons without a challenge, suggest one at their level.
- Very specific: line 148
Evaluate their pipeline: If they have built components but not evaluated, suggest /evaluate.
- Distinctive: line 149
Level up: If they have completed their track, suggest moving to the next difficulty level.
- Distinctive: line 175
If the learner is short on time, suggest focusing on core lessons first: "You can skip optional lessons and come back to them later — the …
- Distinctive: line 181
If the learner asks for a badge (e.g., says "badge" or "readme badge"), generate a shields.io markdown badge they can add to their README:
- Distinctive: line 199
If early: "You're just getting started but you've already got the foundation down.
- Distinctive: line 200
If mid-track: "You're past the basics.
- Distinctive: line 201
If near completion: "You're close.
- Distinctive: line 202
If complete: "You've done the whole thing.
- Distinctive: line 212
Always be encouraging — progress tracking should motivate, not discourage
- Distinctive: line 213
If the learner has been inactive for a while, gently welcome them back without guilt
- Distinctive: line 214
Keep the display clean and scannable — learners should get the picture in seconds
- Distinctive: line 215
If data files are missing or incomplete, work with what is available and note what is missing
“Common” is measured: kept by at least 6 in 10 of the 43 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
Roadmap: Track Your Progress and Plan Ahead
Read the learner's progress data and present a clear picture of where they are, what they have accomplished, and what to do next.
Step 1: Load Progress Data
Read the following files from the progress/ directory:
learner-profile.md— track assignment, start date, backgroundmodule-tracker.md— lesson completion statusquiz-results.md— quiz scores and identified gapschallenges.md— completed challenges and scoresdebug-log.md— debugging sessionspapers-reviewed.md— papers studied
If progress/learner-profile.md does not exist, the learner has not started yet. Suggest running /start to begin their journey.
Step 2: Display Progress Overview
Present a clear summary with module badges and time estimates:
RAG Learning Academy — Your Progress
=====================================
Track: [Beginner/Intermediate/Advanced]
Started: [date] | Days active: [N] | Streak: [N]d
Module Progress:
[===========-------] 58% (21/36 lessons)
Module 1: Foundations [####] Complete ~2h done
Module 2: Document Processing [####] Complete ~3h done
Module 3: Embeddings [##--] 2/4 lessons ~1.5h left
Module 4: Vector Databases [----] Not started ~3h est.
...
Time remaining on your track: ~8.5 hoursModule Completion Badges
When a module is complete, show a badge next to it:
Module 1: Foundations [####] Complete [FOUNDATIONS]
Module 2: Document Processing [####] Complete [DATA WRANGLER]
Module 3: Embeddings [####] Complete [VECTOR NAVIGATOR]Badge names by module:
| Module | Badge |
| 1 | FOUNDATIONS |
| 2 | DATA WRANGLER |
| 3 | VECTOR NAVIGATOR |
| 4 | DB ARCHITECT |
| 5 | RETRIEVAL ENGINEER |
| 6 | PROMPT CRAFTER |
| 7 | QUALITY GUARDIAN |
| 8 | PATTERN MASTER |
| 9 | PRODUCTION READY |
Time Estimates
Estimate time per module based on lesson count and type (core ~45min, optional ~30min). Show:
- Time spent (completed lessons)
- Time remaining (incomplete lessons in track)
- Total track estimate
Use visual progress bars built from ASCII characters. Make the progress feel tangible and motivating.
Step 3: Show Milestone Progress
Read .claude/docs/reference/milestones.md to load the milestone definitions. Based on the learner's track and progress, display their milestone status:
Milestones
==========
✓ Milestone 1: First Light — You built a working RAG system
✓ Milestone 2: Data Wrangler — You can process any document
◐ Milestone 3: Vector Navigator — 3/5 requirements done
○ Milestone 4: Retrieval Engineer — Not startedUse ✓ for complete, ◐ for in-progress (show fraction), ○ for not started. Only show milestones relevant to the learner's track (e.g., Beginner track shows milestones 1-3).
For the current in-progress milestone, show which requirements remain:
Next up for Milestone 3 — Vector Navigator:
- [ ] Complete the "Model Shootout" exercise
- [ ] Pass a quiz on embeddings or vector databasesCelebrate completed milestones warmly. For the current milestone, make the remaining items feel achievable.
Proficiency level display: Also check which proficiency level the learner has earned based on completed milestones (see the "Proficiency Levels" section of milestones.md):
Proficiency Level: RAG Practitioner
✓ RAG Explorer (Milestones 1-2)
✓ RAG Practitioner (Milestones 3-5) ← CURRENT LEVEL
◐ RAG Engineer (Milestones 6-7) ← 1 milestone away
○ RAG Architect (Milestone 8 + bonus)When a learner earns a new level, celebrate it prominently: "Congratulations — you've earned the RAG Practitioner level! You can now design and build real retrieval systems."
Step 4: Highlight Achievements
Call out what the learner has accomplished:
- Total lessons completed
- Module badges earned (list them)
- Current streak (read from
progress/streaks.md) - Longest streak
- Milestones earned
- Quizzes passed (and average score)
- Challenges completed (with difficulty levels)
- Components built via
/build - Papers reviewed
- Debugging sessions completed
If there are notable achievements, celebrate them: "You have completed all beginner challenges — that is a solid foundation."
Also mention bonus milestones (Reviewer, Debugger, Completionist) if the learner is making progress toward them.
Step 5: Identify Knowledge Gaps
Analyze quiz results and challenge scores to find areas where the learner may need more practice:
- Topics with quiz scores below 70%
- Challenge areas where they scored low on specific dimensions
- Modules they skipped or partially completed
- Concepts flagged during debugging sessions
Present these as opportunities, not failures: "You might benefit from revisiting chunking strategies — your quiz score suggests some concepts did not fully click yet."
Step 6: Recommend Next Steps
Based on the progress data, suggest 3-5 specific next actions, prioritized by impact:
- Continue your current module: If a module is in progress, suggest the next lesson.
- Fill a knowledge gap: If quiz results show a weak area, suggest
/explainor/lessonfor that topic. - Take a challenge: If they have completed several lessons without a challenge, suggest one at their level.
- Evaluate their pipeline: If they have built components but not evaluated, suggest
/evaluate. - Level up: If they have completed their track, suggest moving to the next difficulty level.
Each suggestion should include the specific slash command to run.
Step 7: Show the Full Curriculum Map
Display the complete curriculum with the learner's position marked. Indicate core vs optional lessons and show estimated time:
Module 1: RAG Foundations
[x] 1.1 What is RAG? (core, 30m)
[x] 1.2 When to Use RAG (core, 30m)
[x] 1.3 RAG Architecture Overview (core, 45m)
[x] 1.4 Hello World RAG (core, 60m)
Module 2: Document Processing
[x] 2.1 Document Parsing (core, 45m)
[ ] 2.2 Text Preprocessing (optional, 30m)
[x] 2.3 Fixed-Size Chunking (core, 30m)
[ ] 2.4 Recursive Chunking (optional, 45m) <-- YOU ARE HERE
[ ] 2.5 Semantic Chunking (optional, 45m)
...Show a summary at the top: "Core path: ~11 hours | Full curriculum: ~35 hours | Your track: ~X hours remaining"
If the learner is short on time, suggest focusing on core lessons first: "You can skip optional lessons and come back to them later — the core path gives you everything you need to build a working RAG system."
This gives the learner a birds-eye view of the entire journey.
Step 8: GitHub Badge Export
If the learner asks for a badge (e.g., says "badge" or "readme badge"), generate a shields.io markdown badge they can add to their README:
Generate the badge URL dynamically based on their actual progress:
- Color:
8B5CF6(academy purple) for in-progress,22C55E(green) for complete - Label:
RAG Academy - Message:
Module X/9orCompleteif all modules done - Style:
flat-square
Show them the markdown to copy-paste into their project's README.
Step 9: Motivational Close
End with a brief, genuine note based on their progress. Follow the project's voice & tone — real encouragement, not cheerleading:
- If early: "You're just getting started but you've already got the foundation down. The pieces start clicking fast from here."
- If mid-track: "You're past the basics. The stuff you're learning now is what separates 'I followed a tutorial' from 'I actually understand RAG.'"
- If near completion: "You're close. The advanced stuff is where RAG gets genuinely interesting — and where most people never get to."
- If complete: "You've done the whole thing. You know more about RAG than most engineers building it in production. Seriously. Go build something real, or help improve these materials for the next person."
Suggest 2-3 relevant next steps using slash commands, tailored to the specific next action identified in the progress analysis above. For example:
/lesson [next lesson]— continue where you left off in your current module/quiz [weak topic]— strengthen an area where your quiz scores were low/challenge [appropriate level]— put your skills to the test with a real-world challenge
Guidelines
- Always be encouraging — progress tracking should motivate, not discourage
- If the learner has been inactive for a while, gently welcome them back without guilt
- Keep the display clean and scannable — learners should get the picture in seconds
- If data files are missing or incomplete, work with what is available and note what is missing
- Suggest variety in next steps — mix lessons, challenges, and hands-on building
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.

