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

Reflect

ASecurity

Review a scoped conversation for recurring lessons and propose evidence-backed corrections to existing Skills.

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

Security Analysis

A100/100

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

Scanned 10/1/2026

$npx -y skills add williamwue/oh-my-stack --skill reflect --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Reflect?

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

Security grade badge for Reflect
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/williamwue-reflect-61025a7f/badge)](https://www.skillsdirectory.com/skills/williamwue-reflect-61025a7f)

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: reflect
description: Review a scoped conversation for recurring lessons and propose evidence-backed corrections to existing Skills.
---

# Reflect

Use only when the user asks to reflect on an actual conversation or work run.
Trivial exchanges and one-off preferences do not justify durable Skill edits.
Identify the active task transcript through the runtime's task history or the
workspace-scoped transcript path. Do not search unrelated projects or private
history. When no full transcript is accessible, create a bounded digest from
visible context and disclose the loss of tool evidence.

Run three independent read-only reviews when delegation is available: judgment
(wrong decisions and missed evidence), tooling (friction and repeatable checks),
and divergent alternatives. Give each the same frozen task record and require
precise citations, counterexamples, and proposed destination. When available,
use `reflect.tooling` for tooling and `reflect.judgment` for judgment and the
divergent lens; keep all three sessions independent. Use configured routes,
not assumed model identities. With fewer workers, preserve separate
lenses and label reduced independence.

Synthesize Accepted, Rejected, and Backlog findings. Root rechecks each accepted
claim against the transcript and target Skill. Move a finding to Backlog when
a type, schema, lint rule, test, or runtime check enforces it more reliably than
prose. Reject duplicated guidance, subjective one-offs, and changes outside the
user's workspace or intended scope.

Show the proposed edit set with exact paths and the evidence before altering
shared or personal Skills. Apply only changes the user requested or approved;
otherwise return a reviewable proposal. For approved changes, use
[authoring-a-skill](../authoring-a-skill/SKILL.md), validate references and
frontmatter, and test behavioral changes when warranted. Do not assume a team
tracker exists or file external backlog items without authorization. Return
applied edits, proposed edits, rejected findings, and open structural work.

Attribution

williamwuewilliamwue
View sourceSee grades on GitHubMore from williamwue →
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 →