New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Grant Proposal

by pedrohcgs in pedrohcgs/claude-code-my-workflow

Scaffold a research grant proposal (NSF, NIH, ERC, or foundation) by composing existing primitives — pulls identification strategy from an /interview-me spec, delegates the data-management plan to…

MITAuto-check passedResearch & Science

Install Grant Proposal

skills CLI
$ npx skills add pedrohcgs/claude-code-my-workflow --skill grant-proposal -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install pedrohcgs/claude-code-my-workflow grant-proposal --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/pedrohcgs/claude-code-my-workflow.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/grant-proposal .claude/skills/grant-proposal && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
grant-proposal
GitHub stars
1.7k
Token cost
~3.4k tokens
SKILL.md length
1,395 words
Files
1
Skills in repo
59
Repo updated
First seen
Licence
MIT

At a glance

Scaffold a research grant proposal (NSF, NIH, ERC, or foundation) by composing existing primitives — pulls identification strategy from an /interview-me spec, delegates the data-management plan to…

  • Works in 5 steps: Detect funder + spec → Scaffold sections from templates + the… → Compose the DMP and computational… → …
  • User says draft a grant
  • SKILL.md covers When to use, When NOT to use, Funder profiles and Workflow, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Grant Proposal is an agent skill from pedrohcgs/claude-code-my-workflow. Scaffold a research grant proposal (NSF, NIH, ERC, or foundation) by composing existing primitives — pulls identification strategy from an /interview-me spec, delegates the data-management plan to /data-management-plan and the facilities statement to /capture-environment, and emits a funder-requirements checklist. Use when user says "draft a grant", "write a proposal", "NSF proposal", "NIH aims", "ERC application", "foundation grant", "specific aims", or "scaffold a grant proposal". NOT a submission tool —…

Its SKILL.md is about 3.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Research & Science, covering Grant writing and Requirements gathering. The repository describes itself as: A ready-to-fork Claude Code template for academics using LaTeX/Beamer + R. Multi-agent review, quality gates, adversarial QA, and replication protocols. The licence is MIT.

When your agent uses it

  • User says draft a grant
  • Write a proposal
  • ERC application
  • Foundation grant

Example prompts

  • “draft a grant”
  • “write a proposal”
  • “NSF proposal”
  • “/grant-proposal”

Requirements

  • Python 3
  • Pre-approved tools (allowed-tools): Read, Grep, Glob, Write, Agent, Task

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Detect funder + spec
  2. Scaffold sections from templates + the spec
  3. Compose the DMP and computational statements (delegate)
  4. Coherence pass (aims ↔ methods ↔ budget ↔ timeline)
  5. Post-flight verification + output

What it can do on your machine

Read from SKILL.md and the folder at commit ae72617. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Grep
    • Glob
    • Write
    • Agent
    • Task

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Grant Proposal loads about 3.4k tokens when it runs. Until then it costs about 151 tokens; SKILL.md has 1,395 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~151
When it runs · the whole SKILL.md, loaded when a task matches
~3.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from pedrohcgs/claude-code-my-workflow at commit ae72617, republished under its MIT licence (© pedrohcgs). 1,395 words, ~3,385 tokens.

Download SKILL.mdSave it as .claude/skills/grant-proposal/SKILL.md (or your agent's skills folder).
name
grant-proposal
description
Scaffold a research grant proposal (NSF, NIH, ERC, or foundation) by composing existing primitives — pulls identification strategy from an `/interview-me` spec, delegates the data-management plan to `/data-management-plan` and the facilities statement to `/capture-environment`, and emits a funder-requirements checklist. Use when user says "draft a grant", "write a proposal", "NSF proposal", "NIH aims", "ERC application", "foundation grant", "specific aims", or "scaffold a grant proposal". NOT a submission tool — produces a draft the user uploads to the sponsor's portal themselves.
allowed-tools
Read, Grep, Glob, Write, Agent, Task
argument-hint
[--funder nsf|nih|erc|foundation] [--call <file>] [--input <spec>] [--out <dir>] [--no-verify]
disable-model-invocation
true

/grant-proposal — Research Grant Proposal Scaffolder

Compose a funder-shaped grant proposal draft from primitives you already have: an /interview-me research spec supplies the science, /data-management-plan supplies the DMP, /capture-environment supplies the facilities/computational statement, and /lit-review supplies the prior-work framing. This skill structures and stitches — it does not submit anywhere, and it does not invent identification strategy where a spec is absent.

Core principle: A proposal is a coherence artifact. Aims, methods, budget, timeline, and broader impacts must agree with each other and with the underlying research spec. The skill's main value-add over a blank template is the Phase 3 coherence pass (aims ↔ methods ↔ budget ↔ timeline).

When to use

  • Drafting an NSF / NIH / ERC / foundation proposal from an existing research idea.
  • Turning an /interview-me spec (or a /preregister PAP) into a fundable narrative.
  • Assembling the boilerplate-but-required pieces (DMP, facilities, data-sharing) so the human writes only the science.
  • During resubmission, re-scaffolding aims after a reviewer "revise and resubmit" round.

When NOT to use

  • You need the science itself invented — run /interview-me first; this skill refuses to fabricate an identification strategy.
  • The sponsor is a clinical-trial funder requiring its own protocol template (out of scope; use the sponsor's native forms).
  • You want a finished, submittable PDF — this writes Markdown sections + a checklist; final assembly into the sponsor's format is yours.

Funder profiles

Generic across sponsors via placeholder profiles. --funder selects the section set + naming; default is nsf. The profiles are fallbacks for when no call is supplied: the program's own call (--call) always wins.

FunderCore sections (named per sponsor)Page/format signals
nsfProject Summary (Overview/Intellectual Merit/Broader Impacts) · Project Description · Broader Impacts · Data Management & Sharing Plan · Facilities/Equipment · Budget Justification15-page Project Description; DMSP required
nihSpecific Aims (1 p.) · Research Strategy (Significance/Innovation/Approach) · Vertebrate/Human Subjects (if any) · Data Management & Sharing · Facilities & Other Resources · Budget JustificationAims page is load-bearing
ercExtended Synopsis (B1) · Scientific Proposal (B2: state-of-art, objectives, methodology) · CV + track record · Resources/Budget · Data ManagementPI-centric; "high-risk/high-gain" framing
foundationProject Summary · Statement of Need · Goals & Objectives · Methods/Approach · Evaluation Plan · Budget Justification · SustainabilityMission-fit framing; lighter methods

Economics framing is the primary lens (DiD/event-study, IV, RCT, panel; AEA Data Editor / openICPSR / DCAS data-sharing expectations), but the section scaffold is field-agnostic — a biology or CS forker fills the same slots.

Workflow

Phase 0 — Detect funder + spec
  1. Resolve --funder (or infer from the request wording; default nsf). Echo the chosen profile back before drafting.
  2. Locate the research spec: --input <path>, else the most recent quality_reports/specs/research_spec_*.md from /interview-me. If none exists, stop and recommend /interview-me — do not invent the science.
  3. From the spec, extract: research question, hypotheses (directional), identification strategy (DiD / IV / RDD / RCT / structural), data sources, sample, expected results, contribution. Record the spec's **Paper type:** value if present (the header line /interview-me writes; accept a paper_type: field in a hand-written spec too).
  4. The program's call. Ask once for the actual solicitation, NOFO, RFP or work-programme text (--call <file>, PDF or text — Read handles both). When given, take from it the required sections and documents, the page or word limits, and the review criteria, quoting its wording with a page reference; never paraphrase a limit. When none is given, continue with the generic profile and say so in the output header.
  5. Scan quality_reports/ for adjacent artifacts to reuse: a /lit-review synthesis (prior work), a /preregister PAP (analysis plan), a passport.yaml or /data-analysis outputs (preliminary results).
Phase 1 — Scaffold sections from templates + the spec

Generate the funder's section set. Map spec content into slots:

  • Specific Aims / Project Summary — RQ + 2–3 numbered, directional aims drawn from the spec's hypotheses.
  • Background & Significance — motivation + prior work; pull citations from the /lit-review synthesis if present (do not re-search unless asked).
  • Research Design & Methods — lift the identification strategy verbatim from the spec (estimand, treatment/control, identifying assumption, robustness and placebo strategy, clustering). Name the estimator concretely (e.g. fixest::feols, AER::ivreg, Stata reghdfe).
  • Preliminary Results — summarize any existing /data-analysis / passport outputs; otherwise mark [PRELIMINARY RESULTS: none yet — describe planned pilot].
  • Timeline & Milestones — quarter/year table aligned to the aims (every aim gets a milestone).
  • Broader Impacts / Significance — sponsor-appropriate framing (NSF Broader Impacts vs NIH Significance vs foundation mission-fit).
  • Budget Justification skeleton — personnel / data acquisition / compute / travel / dissemination line-item stubs, each tied to an aim.

For every MUST slot the spec did not supply, write [CLARIFY: <specific question>] — never fabricate. Re-use the MUST / SHOULD / MAY clarity language from templates/requirements-spec.md.

Phase 2 — Compose the DMP and computational statements (delegate)
  1. Data Management (& Sharing) Plan — spawn an Agent that reads /data-management-plan's SKILL.md and follows it with the funder + data sources from the spec (that skill is user-invoked only — disable-model-invocation — so it is followed, not invoked). It returns the DMP section (repository choice — openICPSR / Dataverse / Zenodo, access/retention, FAIR/DCAS alignment). If any data source is sensitive (restricted-use admin data, PII, IRB-restricted), have it honor .claude/rules/confidential-data.md and describe access via a secure enclave / FSRDC rather than open release. Do not draft a sharing plan that promises to release confidential data.
  2. Facilities / Computational-Environment statement — invoke /capture-environment via the Agent tool to produce the compute/software/dependency statement (cluster, R/Stata/Python toolchain, renv.lock / DESCRIPTION / requirements.txt provenance) for the Facilities section.

If a delegate skill is unavailable, leave a [DELEGATE: /data-management-plan] placeholder rather than half-writing its output.

Show full SKILL.md (533 more words)Show less
Phase 3 — Coherence pass (aims ↔ methods ↔ budget ↔ timeline)

The differentiating step. Cross-check the assembled draft and report mismatches:

  • Aims ↔ Methods — every aim has a named method/estimator; no orphan method serves no aim.
  • Methods ↔ Budget — each cost line traces to an aim (e.g. an RCT aim implies a participant-incentives line; admin data implies an acquisition/enclave line; a large simulation implies a compute line).
  • Aims ↔ Timeline — every aim has at least one milestone; no milestone is unattributed.
  • DMP ↔ Methods — the data named in Methods matches the data described in the DMP; confidential sources are not promised as open.
  • Page/format budget — flag sections likely to overflow the page limit — the call's own limits when one was given, else the profile's (NSF 15-page Project Description, NIH 1-page Aims). With a call, also confirm every required section is present and every review criterion is addressed somewhere, citing the call's page.
Phase 4 — Post-flight verification + output
  • Post-flight (CoVe): if Background/Significance cites prior literature, run the Post-Flight protocol from .claude/rules/post-flight-verification.md — spawn claim-verifier via the Agent tool (fresh context, never a conversation fork) on the citations. Surface PASS / PARTIAL / FAIL. Skip on --no-verify or zero citations.
  • Write sections to --out (default quality_reports/grants/YYYY-MM-DD_<slug>/), one Markdown file per section plus checklist.md.

Output / Report format

A proposal_draft.md (concatenated sections) plus a checklist.md:

markdown
# Grant Proposal Draft — [Title]
**Funder:** NSF | NIH | ERC | foundation     **Date:** YYYY-MM-DD
**Source spec:** quality_reports/specs/research_spec_<slug>.md
**Call:** <path> (read YYYY-MM-DD) | NOT PROVIDED — structure from the generic <funder> profile

## Funder-Requirements Checklist
| Requirement | Status | Source |
|---|---|---|
| Project Summary / Specific Aims | DRAFTED | Phase 1 |
| Research Design & Methods | DRAFTED | spec |
| Data Management & Sharing Plan | DELEGATED | /data-management-plan |
| Facilities / Computational Env | DELEGATED | /capture-environment |
| Budget Justification | SKELETON | Phase 1 |
| Broader Impacts / Significance | DRAFTED | Phase 1 |
| [n] [CLARIFY:] items unresolved | TODO | — |

## Coherence Report
- Aims ↔ Methods: PASS / [n issues]
- Methods ↔ Budget: PASS / [n issues]
- Aims ↔ Timeline: PASS / [n issues]
- DMP ↔ Methods (confidential-data check): PASS / [n issues]
- Page-budget flags: [sections at risk of overflow]

## Post-Flight Verification
Claims extracted: N · Verified: N · Outcome: PASS / PARTIAL / FAIL

Exit behavior

  • All MUST slots filled + coherence PASS: report "DRAFT READY — review [CLARIFY:] items, then assemble in the sponsor's portal."
  • Open [CLARIFY:] / [DELEGATE:] items or coherence issues: report "INCOMPLETE — N items unresolved" and list them. The skill never blocks like /audit-reproducibility (it is a drafting tool, not a gate) — it surfaces, the author resolves.
  • No research spec found: stop in Phase 0 and recommend /interview-me. Nothing is written.

Flags

  • --funder <nsf|nih|erc|foundation> — Select the funder profile that shapes section structure and the requirements checklist.
  • --call <file> — The program's solicitation / NOFO / RFP (PDF or text). Its required sections, limits and review criteria override the generic profile. Default: none — the generic profile is used and the header says so.
  • --input <spec> — Path to an /interview-me research spec to seed Aims and Methods. Default: the newest quality_reports/specs/research_spec_*.md; if none exists, stop and recommend /interview-me.

Cross-references

What this skill does NOT do

  • Submit anywhere. It writes Markdown + a checklist; you assemble and upload to Research.gov / ASSIST / the ERC portal / the foundation's system.
  • Invent the science. No spec → no proposal. It will not fabricate an identification strategy, hypotheses, or aims.
  • Write the DMP or facilities statement itself. Those are delegated to /data-management-plan and /capture-environment; this skill only stitches their output into the funder's section set.
  • Compute the budget. It scaffolds line items tied to aims; actual dollar figures, indirect-cost rates, and effort percentages are the PI's and the grants office's job.
  • Guarantee page-limit compliance. It flags likely overflow; final trimming to the sponsor's exact format is manual.

© pedrohcgs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/grant-proposal of pedrohcgs/claude-code-my-workflow.

Open the folder on GitHubat commit ae72617

Compare with similar skills

Grant Proposal next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Grant Proposal compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Grant Proposal this skillpedrohcgs/claude-code-my-workflow1.7k—~3.4kAutomated safety check: PassMIT
Grantsalirezarezvani/claude-skills28k—~3.7kAutomated safety check: PassMIT
Scientific Venue Templatesdavila7/claude-code-templates32k9 repos~5.1kAutomated safety check: NotesMIT
Academic HumanizerAIScientists-Dev/academic-humanizer1.9k1 repos~4.2kAutomated safety check: PassMIT
NSFC Literature Review WriterHuiyuLi-2000/Chinese-Grant-Writer-Skills4341 repos~1.4kAutomated safety check: NotesMIT
NSFC Grant Rationale Writerhuangwb8/ChineseResearchLaTeX2.9k—~945Automated safety check: PassMIT

Similar skills

  • Grants

    alirezarezvani/claude-skills

    NIH grant research skill for clinical researchers. An agent skill from alirezarezvani/claude-skills.

    28k GitHub stars~3.7k tokensUpdated 1 mo ago
    Documents & OfficeAuto-check passed

  • Scientific Venue Templates

    davila7/claude-code-templates

    Supplies LaTeX templates and formatting rules for journals, conferences, posters, and grant proposals, then can check a draft against them.

    32k GitHub starsUsed in 9 repos~5.1k tokens
    Research & ScienceAuto-check: notes

  • Academic Humanizer

    AIScientists-Dev/academic-humanizer

    Improve the clarity and voice of AI-assisted academic writing (papers, theses, rebuttals) and funding proposals (NSF Project Summary/Description, NIH Specific Aims): preserve scholarly conventions…

    1.9k GitHub starsUsed in 1 repo~4.2k tokens
    Research & ScienceAuto-check passed

  • NSFC Literature Review Writer

    HuiyuLi-2000/Chinese-Grant-Writer-Skills

    Writes the research-status literature review and critique section of an NSFC grant proposal, backed by a bundled multi-source literature search.

    434 GitHub starsUsed in 1 repo~1.4k tokens
    Research & ScienceAuto-check: notes

  • NSFC Grant Rationale Writer

    huangwb8/ChineseResearchLaTeX

    Writes, restructures, reviews and polishes the rationale section of NSFC research grant applications in LaTeX, with backups and a diff before every write.

    2.9k GitHub stars~945 tokensUpdated 5 days ago
    Research & ScienceAuto-check passed

  • NSFC Abstract Writer

    huangwb8/ChineseResearchLaTeX

    Writes Chinese and English abstracts for NSFC grant applications, with a recommended title and five alternatives, within set character limits.

    2.9k GitHub starsUsed in 1 repo~1.3k tokens
    Research & ScienceAuto-check passed

More from pedrohcgs/claude-code-my-workflow

All 59 skills in this repo

  • Devils Advocate

    pedrohcgs/claude-code-my-workflow

    Adversarial 5-7 question challenge to a deck's pedagogical choices — ordering, prerequisites, cognitive load, motivation.

    1.7k GitHub starsUsed in 2 repos~641 tokens
    Auto-check passed

  • Vaccinate

    pedrohcgs/claude-code-my-workflow

    Qualify a check before it is allowed to clear anything — prove it can detect the failure it is meant to catch.

    1.7k GitHub stars~2.1k tokensUpdated 12 days ago
    Auto-check: notes

  • Compile Latex

    pedrohcgs/claude-code-my-workflow

    Compile a Beamer LaTeX slide deck with XeLaTeX (3 passes + bibtex).

    1.7k GitHub starsUsed in 1 repo~492 tokens
    Auto-check: notes

  • Context Status

    pedrohcgs/claude-code-my-workflow

    Show current context status and session health. An agent skill from pedrohcgs/claude-code-my-workflow.

    1.7k GitHub starsUsed in 1 repo~613 tokens
    Auto-check: notes

  • Capture Environment

    pedrohcgs/claude-code-my-workflow

    Snapshot the computational environment for a replication package — detects the analysis stack (R / Stata / Python) and emits the right lockfiles (renv.lock + sessionInfo.txt, requirements.txt /…

    1.7k GitHub stars~2.8k tokensUpdated 12 days ago
    Auto-check: notes

  • Checkpoint

    pedrohcgs/claude-code-my-workflow

    Save a structured state snapshot before stopping or handing off.

    1.7k GitHub stars~2.8k tokensUpdated 12 days ago
    Auto-check: notes

Categories

Questions about Grant Proposal

What does Grant Proposal do?

Scaffold a research grant proposal (NSF, NIH, ERC, or foundation) by composing existing primitives — pulls identification strategy from an /interview-me spec, delegates the data-management plan to…. Grant Proposal is an agent skill from pedrohcgs/claude-code-my-workflow. Scaffold a research grant proposal (NSF, NIH, ERC, or foundation) by composing existing primitives — pulls identification strategy from an /interview-me spec, delegates the data-management plan to /data-management-plan and the facilities statement to /capture-environment, and emits a funder-requirements checklist.

When should I use Grant Proposal?

Grant Proposal fits situations like: user says draft a grant; write a proposal; ERC application; foundation grant.

How do I install Grant Proposal in Claude Code?

Run `npx skills add pedrohcgs/claude-code-my-workflow --skill grant-proposal -a claude-code`. Or copy the skill folder (.claude/skills/grant-proposal in pedrohcgs/claude-code-my-workflow) into .claude/skills/grant-proposal in your project. Claude Code loads it when a task matches its description.

How do I install Grant Proposal in Codex?

Run `npx skills add pedrohcgs/claude-code-my-workflow --skill grant-proposal -a codex`. Or copy the skill folder (.claude/skills/grant-proposal in pedrohcgs/claude-code-my-workflow) into .agents/skills/grant-proposal in your project. Codex loads it when a task matches its description.

Can I use Grant Proposal in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add pedrohcgs/claude-code-my-workflow --skill grant-proposal -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/grant-proposal, .gemini/skills/grant-proposal, .github/skills/grant-proposal and .opencode/skills/grant-proposal in your project.

What does Grant Proposal need to run?

SKILL.md names no scripts, command-line tools or credentials: Grant Proposal is instructions for the agent only. Our summary lists: Python 3. Its frontmatter pre-approves these tools: Read, Grep, Glob, Write, Agent, Task.

Does Grant Proposal access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Grant Proposal safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Grant Proposal use?

Grant Proposal is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Grant Proposal use?

About 3.4k tokens (SKILL.md is roughly 14k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Grant Proposal?

Skills that share tags, products or a category with Grant Proposal: Grants (alirezarezvani/claude-skills, 28k stars), Scientific Venue Templates (davila7/claude-code-templates, 32k stars), Academic Humanizer (AIScientists-Dev/academic-humanizer, 1.9k stars) and NSFC Literature Review Writer (HuiyuLi-2000/Chinese-Grant-Writer-Skills, 434 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Grant Proposal?

pedrohcgs (a GitHub user) maintains it in pedrohcgs/claude-code-my-workflow, which has 1,653 GitHub stars. The repository holds 59 skills in this directory. The repository was last updated on September 27, 2026.

Source: pedrohcgs/claude-code-my-workflow on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.