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

Baseline

ASecurity

TRIGGER when: asked to clarify or improve the explanation in existing documentation or a PR-description draft, including a PR URL or pasted body. Saves results locally. Grounds edits in requirements and source while preserving technical meaning. Not for code, config, generic response brevity, or agent instructions. Explicit instruction or SKILL.md targets receive a /kk:implement suggestion without edits or automatic handoff.

150 stars
0 votes
0 copies
1 views
Added 10/2/2026
ai-agentsdocumentation

Security Analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned 10/2/2026

$npx -y skills add serpro69/claude-toolbox --skill baseline --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Baseline?

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

Security grade badge for Baseline
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/serpro69-baseline/badge)](https://www.skillsdirectory.com/skills/serpro69-baseline)

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: clarify-docs
description: |
  TRIGGER when: asked to clarify or improve the explanation in existing documentation
  or a PR-description draft, including a PR URL or pasted body. Saves results locally.
  Grounds edits in requirements and source while preserving technical meaning. Not for
  code, config, generic response brevity, or agent instructions. Explicit
  instruction or SKILL.md targets receive a /kk:implement suggestion without edits
  or automatic handoff.
---

# Clarify Documentation and PR Drafts

Improve an existing document so its intended reader can understand the underlying
work. Produce a local edit; success depends on comprehension and fidelity, with no
document-length target.

## Inputs and boundaries

Accept local documentation files, local PR drafts, a PR URL or pasted PR body, plus any
audience, purpose, requirements and source references. Examples:

- `/kk:clarify-docs docs/configuration.md for service owners; use src/config/`
- `/kk:clarify-docs docs/feat/wip/import/design.md for the implementing developer`
- `/kk:clarify-docs pr-draft.md for repository reviewers; use the actual PR base/head`
- `/kk:clarify-docs <PR URL>; save the revised body to docs/feat/wip/import/pr-draft.md`

A directory permits discovery and selection, not a bulk rewrite. If selection is
consequentially ambiguous, ask which artifact to edit. Related requirements and
code may be read as evidence; only selected documentation may be changed.

Edit an existing local draft in place. For remote or pasted input, use the caller's
destination or name a local draft under the clearly established current feature
directory. If neither is clear, ask before writing. Check for an existing file:
overwrite only the selected draft, never unrelated content; otherwise choose an
unused name within that feature scope or clarify the destination. Obtain remote
bodies and review context through available read-only tools during the shared
procedure's source-reading phase. Reading a PR grants no publishing authority.

Code, config, agent instructions (including `AGENTS.md` and `CLAUDE.md`), skill
instructions are outside this entry point's scope. An
explicit instruction-editing request receives an explanation of this boundary and
a suggestion to use `/kk:implement`; do not invoke it or edit the target. Ordinary
code requests and generic requests for shorter answers do not activate this skill.

## Workflow

**Mandatory order — instructions before action.** Follow this flow strictly in
sequence. Load this file and the entire shared procedure before content-level
target/source reads, editing or verification. Only filenames and request keywords
may be used for early scope selection.

1. Load [shared-document-clarity.md](shared-document-clarity.md) in full.
2. Resolve the selected artifacts, reader, purpose and destination from the request
   and repository instructions. Reuse known answers; clarify consequential gaps.
3. Apply the shared procedure in order: understand the relevant work, establish
   protected meaning, edit for the reader, then verify comprehension and fidelity.
4. Report changed paths and material unresolved gaps briefly. If no edit was needed,
   say so. Produce no additional summary or claim-ledger file.

The shared procedure performs no profile detection and invokes no consumer skill.
Verification is an in-session check; the caller retains responsibility for normal
document review. This entry point adds no independent runtime review gate and makes
no external writes, publication, deployment or implementation changes.
PR updates, comments and messages remain separate actions outside this workflow.

Attribution

serpro69serpro69
View sourceSee grades on GitHubMore from serpro69 →
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', ...

698461 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 →