make-cl
Skill234 starsChanged 8 months agoMITView on GitHub
Generate a tailored cover letter from an existing session file and finished resume/CV
In this repository6 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- critiqueSkill
- edit-resumeSkill
- make-resumeSkill
- setup-build-kbSkill
- setup-extractSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
25 rules. About 0 are common, 16 are distinctive, and 9 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈16
Distinctive · estimate
This author's own choices. Worth a look.
9
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 21
Read config.md Provenance Flags before generating any content.
- Very specific: line 23
Use the email from config.md Personal Info in all outputs
- Distinctive: line 31
If the user provides feedback, corrections, or suggestions at any point:
- Distinctive: line 33
If it affects already-written content: fix it, re-verify word count and anti-patterns
- Distinctive: line 34
If it changes the framing: note the change in session file Framing Strategy
- Distinctive: line 35
Never restart — resume from current position
- Very specific: line 41
Read resume_builder/reference/shared_ops.md for session startup and file derivation.
- Distinctive: line 44
Read CLAUDE.md — check Active Sessions and KB Corrections
- Very specific: line 45
Read config.md — load Provenance Flags, email, role types
- Very specific: line 48
If CL Status is DONE → "CL already generated.
- Very specific: line 49
If CL Status is IN_PROGRESS → check if CL .tex exists, offer to resume or regenerate
- Very specific: line 50
If Resume Status is not DONE → "Resume not yet generated.
- Distinctive: line 51
If CL Status is PENDING → proceed to Phase 1
- Distinctive: line 57
Read in this order:
- Very specific: line 63
All significance files from resume_builder/support/significance_*.md
- Very specific: line 65
Update session file Status: Cover Letter: IN_PROGRESS
- Distinctive: line 81
Use significance files for field-context depth (NOT resume bullet text)
- Distinctive: line 82
Use session file CL hooks and "why them" angle
- Distinctive: line 83
Ensure every major claim is traceable to a resume/CV bullet
- Distinctive: line 103
Do NOT present the CL draft to the user until all hooks are verified or flagged.
- Distinctive: line 113
Use Read tool to view compiled PDF.
- Distinctive: line 125
Add CL to Output Files
- Distinctive: line 127
Add Next Critique command
- Distinctive: line 135
If user requests changes: apply them, re-compile, re-verify.
- Distinctive: line 136
If user approves: update Status, present next command.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/make-cl
User input: $ARGUMENTS
Parse $ARGUMENTS:
- Session file path (e.g.,
output/Acme/session_acme_engineer.md) → read that session file - Session name (e.g.,
acme_engineer) → find session file via shared_ops.md derivation - Empty → check
CLAUDE.mdActive Sessions for latest
Safety Rules (ALWAYS ENFORCED)
Accuracy > Relevance > Impact > ATS > Brevity
Read config.md Provenance Flags before generating any content. Verify every claim against that table.
- Use the email from
config.mdPersonal Info in all outputs - CL deepens what resume presents — never introduces new claims not traceable to resume bullets
- Source field context from
resume_builder/support/significance_*.mdfiles
User Input During Execution
If the user provides feedback, corrections, or suggestions at any point:
- Acknowledge the input immediately
- If it affects already-written content: fix it, re-verify word count and anti-patterns
- If it changes the framing: note the change in session file Framing Strategy
- Never restart — resume from current position
Startup
Read resume_builder/reference/shared_ops.md for session startup and file derivation.
Then:
- Read
CLAUDE.md— check Active Sessions and KB Corrections - Read
config.md— load Provenance Flags, email, role types - Find and read the session file
- Recovery check:
- If CL Status is DONE → "CL already generated. Run
/critiquenext." Show next command. Stop. - If CL Status is IN_PROGRESS → check if CL .tex exists, offer to resume or regenerate
- If Resume Status is not DONE → "Resume not yet generated. Run
/make-resumefirst." Stop. - If CL Status is PENDING → proceed to Phase 1
- If CL Status is DONE → "CL already generated. Run
Phase 1: Load Context
Read in this order:
- Session file — specifically: Company Context, Cover Letter Plan, Framing Strategy, ATS Keywords
- Finished resume/CV .tex — path from session file Output Files. Read to understand what CL must complement.
resume_builder/reference/cl_reference.md— CL format rules, paragraph templates, anti-patternsresume_builder/support/ai_fingerprint_rules.md— Banned words, structural rules (CLs are most vulnerable)- The matching bundle from session file role type →
resume_builder/bundles/bundle_[role_type].md— Section 5 (Cover Letter) - All significance files from
resume_builder/support/significance_*.md
Update session file Status: Cover Letter: IN_PROGRESS
Progress: "Loading CL context — [company], [role type] bundle, [institution type]..."
Phase 2: Generate Cover Letter
Read resume_builder/templates/coverletter_template.tex.
Detect institution type from session file Cover Letter Plan:
- Industry → 3 paragraphs, 250-300 words
- National Lab → 4 paragraphs, 350-450 words
- Academic → 4 paragraphs, 350-450 words (postdoc) or 450-650 words (faculty)
Generate CL following cl_reference.md paragraph structure:
- Use significance files for field-context depth (NOT resume bullet text)
- Use session file CL hooks and "why them" angle
- Ensure every major claim is traceable to a resume/CV bullet
- Open with a specific reference to their work — no generic openers
- Weave credentials into body paragraphs, not closing
Save to output/<FolderName>/e2e_<name>_cover_letter.tex
Progress: "Writing [institution type] cover letter — [N] paragraphs, targeting [N] words..."
CL Hook Verification Gate (MANDATORY before presenting to user)
Web-search every hook used in the CL:
- Academic: PI name + cited paper/research area
- National Lab: named program, thrust area, or group publication
- Industry: product, technology, or company news referenced
Present evidence as:
Claim: [what the CL says] → Evidence: [what the search found] → Source: [URL]
Flag any unverified item: "UNVERIFIED — please confirm"
Do NOT present the CL draft to the user until all hooks are verified or flagged.
Phase 3: Compile & Verify
pdflatex -interaction=nonstopmode -output-directory=output/<FolderName> output/<FolderName>/e2e_<name>_cover_letter.texUse Read tool to view compiled PDF. Verify:
| Gate | Check | If FAIL |
| Word count | Industry 250-300, Lab/Academic 350-450 | Trim/expand |
| Page count | Resume package: 1 page. CV package: 1-2 pages | Adjust content |
| Page fill | 1pg: well-filled. 2pg: page 2 >= half filled before signature | Adjust |
| Anti-patterns | No generic opener, no defensive framing, no credential dump | Rewrite |
| Package cohesion | CL claims traceable to resume bullets, no contradictions | Fix |
| Compile | Clean pdflatex | Fix LaTeX errors |
Update session file:
- Add CL to Output Files
- Status:
Cover Letter: DONE - Add Next Critique command
Progress: "Compiled — 1 page, 278 words. Package cohesion verified."
>>>>>> MANDATORY STOP — DO NOT PROCEED <<<<<<
Present: CL summary (word count, page count, key hooks used). You MUST wait for the user's explicit text response before continuing.
If user requests changes: apply them, re-compile, re-verify. Update session file. If user approves: update Status, present next command.
Do NOT trigger file organization — that happens after /critique approval.
"Cover letter done. Next steps:
- /clear
- [exact /critique command with session file path]"
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.

