mcpField
S
scribe

scribe

github.com/akshay-diwadkarDocuments173 installsUpdated today
Repository

About scribe

scribe is a skill for creating or auditing technical documents from supplied sources. It focuses on traceable, executable instructions while preserving source details and reporting unresolved gaps.

Key features

  1. 01Create or revise documents in place
  2. 02Trace document content to bound sources
  3. 03Check commands, paths, values, and ordering
  4. 04Audit documents without modifying them

Use cases

  1. 01Write technical instructions from supplied references
  2. 02Revise an existing document against source material
  3. 03Audit document coverage and report content gaps

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/akshay-diwadkar/first-four-hours --skill scribe

After installing, type/scribein Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

skill-protocol.json
agents/
openai.yaml
references/
audit.md
document-bundle.md
mte-1.md
source-grounding.md
write.md
schemas/
document-bundle.schema.json
glossary.schema.json
scripts/
_diagnostic_contract.py
_document_contract.py
_skill_protocol_runtime.py
audit_document.py
bundle_workspace.py
check_document_language.py
check_document.py
cli.py
seal_document.py
templates/
document-bundle.json

Details

From the project README

Scribe

Purpose and authority

Turn supplied technical sources into a document its reader can execute and trace. Never invent source facts; preserve bound commands, paths, values, ordering, warnings, and recovery. Validation does not establish independent factual truth.

Write only with document-creation or revision authority; implicit invocation never grants write or remediation authority. Audit is a separate operation that writes only its report. Audit must not modify the document, bundle, or bound sources.

Derive audience, reader job, and scope from the request and sources. Ask the user only for a material publication or content-policy choice the sources cannot settle; a missing source fact is an unresolved gap. Consult reason before committing to a document plan, after a failure or direction change, and before reporting completion. Final and stop reports trace reason checkpoints per its Checkpoint trace.

Write and audit

Each document is a deliverable: in write mode, create or edit the actual file in place where the user wants it. Both operations check every document one document-bundle.json lists against the sources it binds, per Document Bundle and Source Grounding. The bundle is support state: write it from templates/document-bundle.json in a temporary directory outside the repository. List several documents to handle them in one run.

To write, follow Write; its language checks apply MTE-1, an original contract only inspired by ASD-STE100: never claim official ASD-STE100 compliance or imply that this skill contains its approved-word dictionary. The write command only checks the documents and edits no file:

python /absolute/skill-root/scripts/cli.py --repo-root /absolute/repo \
  --input bundle=/absolute/temp/document-bundle.json --format json write

To audit, follow Audit: run audit the same way with --input slug=<audit-slug>. It writes only .first-four-hours/scribes/<slug>/scribe-audit.md, one section per document.

Completion

Write completes only when write returns result.status: complete. On incomplete, only the listed gaps remain: report each with its owner. Otherwise repair the document each diagnostic's document names, or the bundle, as its required_action directs, then rerun. Audit completes only when audit returns status: complete; report the scribe-audit.md path and each document's document_sha256 and findings. A passing result is not completion while a material reader job stays unsupported: report the exact gap and its next owner. End with one optional next step fitting this outcome: a fenced, self-contained prompt naming any repository, issue, PR, or artifact it needs, or say none is needed. Only a "yes" starts it, via any skill it names, but the user runs a charter, diagnose, or ticket step as its /<skill> command.

Comments

Markdown supported