Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Agentic Doc Ingest

ASecurity

Turn the charter, decision log and unit records of a completed feature into documentation — user-facing guides or technical notes — without reading the implementation. Use when a feature built through the agentic development pipeline is finished and needs documenting, when the user says "document that feature", "update the docs for X", or "what did we actually ship". Runs downstream of and independently from the pipeline, so it can be re-run months later.

316 stars
0 votes
0 copies
0 views
Added 9/23/2026
ai-agentsgodocumentation

Security Analysis

A100/100

Scanned 9/23/2026

$npx -y skills add PackmindHub/packmind --skill agentic-doc-ingest --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Agentic Doc Ingest?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Agentic Doc Ingest
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/packmindhub-agentic-doc-ingest/badge)](https://www.skillsdirectory.com/skills/packmindhub-agentic-doc-ingest)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: 'agentic-doc-ingest'
description: 'Turn the charter, decision log and unit records of a completed feature into documentation — user-facing guides or technical notes — without reading the implementation. Use when a feature built through the agentic development pipeline is finished and needs documenting, when the user says "document that feature", "update the docs for X", or "what did we actually ship". Runs downstream of and independently from the pipeline, so it can be re-run months later.'
---

# Documentation ingest

You write documentation from three files and no code:

```
.claude/features/<slug>/charter.md      what was meant to be built, and for whom
.claude/features/<slug>/decisions.md    what was decided, and what was rejected
.claude/features/<slug>/records.jsonl   what each unit actually did
```

## Why you do not read the code

Because you do not have to, and that is deliberate. The records carry
`public_surface_changed` and `behaviour_delta` on every unit — the executor
filled them in while it still had the change in front of it, which is the
cheapest and most accurate moment that information exists.

Read a source file only to check a specific name or signature you are about to
print. Not to survey, not to "understand the feature".

## Why the decision log alone is not enough

**The decision log records intent. Documentation built from it describes what
was meant, not what was built.**

The `deviations` field across the records is exactly that gap. Read it early —
where a unit deviated, the log is wrong and the record is right, and a document
that follows the log will confidently describe something that does not exist.

## The two documents are not the same document

Decide which you were asked for; do not blend them.

**User-facing.** Driven by acceptance criteria marked `user-visible: yes` and
decisions marked `user-visible: yes`. Task-oriented, no implementation detail.
For Packmind this lands in `apps/doc/` — hand off to the
`creating-end-user-documentation-for-packmind` skill for house style and
placement rather than inventing your own.

**Technical.** Driven by `public_surface_changed` across the records, plus the
decisions and their rejected alternatives. Rationale is already written in the
decision log — link to it, do not paraphrase it into prose that will drift.

## The coverage check

Before you finish, verify: **every entry marked `user-visible: yes`, in both the
charter and the decision log, has a corresponding mention in what you wrote.**

List the ones that do not, and say why you left them out. This cannot tell you
the documentation is *good* — nothing mechanical can — but omission is the
common failure and this catches it.

## Output

Write the files. Do not commit them.

This pass has a weak exit criterion by nature, and auto-committed prose from a
weakly-gated pass is how documentation quietly becomes wrong. Leave the diff in
the working tree, say what you wrote and what the coverage check found, and let
the human read it.

Attribution

PackmindHubPackmindHub
View sourceSee grades on GitHubMore from PackmindHub →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →