agent-retrospective
Analyzes repeated agent failures or noisy routing and proposes evidence-backed changes to instructions, skills, gates, or runbooks.
Skill by Mesteriis
Chalk Labs
Need help deploying agent-retrospective?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/mesteriis-agent-retrospective
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/agent-retrospective
What's inside
- Skill name
agent-retrospective- Description
- Analyzes repeated agent failures or noisy routing and proposes evidence-backed changes to instructions, skills, gates, or runbooks.
- License
- MIT
- Instructions
- 27 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
# Agent Retrospective Turn repeated agent failure into a small process fix. ## Workflow 1. Identify the failure pattern from actual evidence. 2. Separate one-off mistakes from durable routing or instruction problems. 3. Propose the smallest instruction, skill, or validation update. 4. If editing instructions, use `agents-md-retrospective`. 5. Record validation or explain why only a documentation change was possible. ## Output - failure pattern - root cause category - proposed fix - files to edit - validation plan - residual risk ## Rule Do not add broad personality prompts. Improve routing, evidence requirements, or validation gates instead.
From Mesteriis/Engineering-Bible-AI, MIT.
More from Mesteriis/Engineering-Bible-AI
- 0.567score
architecture-normalizer
Mesteriis
Decomposes large modules, god files, classes, or packages in reviewable steps while preserving public APIs.
SkillAFreshness: AClaude Code +9 - 0.564score
code-wiki-ru
Mesteriis
Builds and validates Russian Obsidian repository wikis, architecture docs, and code/docs/ADR drift reports.
SkillAFreshness: AClaude Code +9 - 0.561score
authz-boundary-review
Mesteriis
Reviews authorization, tenant isolation, roles, ownership, row access, admin boundaries, sharing, and privilege escalation.
SkillAFreshness: AClaude Code +9 - 0.561score
design-system-extractor
Mesteriis
Extracts tokens, typography, spacing, component states, assets, layout, responsive rules, and interactions from a UI reference.
SkillAFreshness: AClaude Code +9 - 0.561score
code-quality
Mesteriis
Reviews cohesion, naming, responsibility, complexity, and maintainability.
SkillAFreshness: AClaude Code +9 - 0.561score
agent-squad
Mesteriis
Plans parallel agents or worktrees with isolated ownership, validation lanes, and merge rules.
SkillAFreshness: AClaude Code +9 - 0.561score
accessibility-ui-review
Mesteriis
Reviews UI accessibility: keyboard, focus, semantics, labels, contrast, motion, forms, dialogs, tables, and screen readers.
SkillAFreshness: AClaude Code +9 - 0.561score
architecture-principles
Mesteriis
Guides module boundaries, dependency direction, and domain structure.
SkillAFreshness: AClaude Code +9 - 0.558score
dependency-advisory-audit
Mesteriis
Triages CVEs and advisories for affected versions, reachability, exploitability, upgrades, and validation.
SkillAFreshness: AClaude Code +9 - 0.558score
code-to-figma
Mesteriis
Routes code-to-Figma work to original native Code Connect or design-generation skills with owner scope rules.
SkillAFreshness: AClaude Code +9 - 0.558score
core-engineering
Mesteriis
General implementation only when no narrower task or ecosystem skill fits.
SkillAFreshness: AClaude Code +9 - 0.558score
deserialization-parser-review
Mesteriis
Reviews parsers, deserialization, uploads, archives, YAML/JSON/XML/pickle, paths, templates, SSRF, and unsafe loaders.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 10, 2026 (3 months ago)
- Last release
- Oct 3, 2026 (28 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Mesteriis
- 0.591score
TG multi-account MCP
Mesteriis
Self-hosted, consent-based access to Telegram accounts and bots for MCP clients
ConnectorAFreshness: ARemote↓ 76/wk - 0.567score
architecture-normalizer
Mesteriis
Decomposes large modules, god files, classes, or packages in reviewable steps while preserving public APIs.
SkillAFreshness: AClaude Code +9 - 0.564score
code-wiki-ru
Mesteriis
Builds and validates Russian Obsidian repository wikis, architecture docs, and code/docs/ADR drift reports.
SkillAFreshness: AClaude Code +9 - 0.561score
agent-squad
Mesteriis
Plans parallel agents or worktrees with isolated ownership, validation lanes, and merge rules.
SkillAFreshness: AClaude Code +9 - 0.561score
code-quality
Mesteriis
Reviews cohesion, naming, responsibility, complexity, and maintainability.
SkillAFreshness: AClaude Code +9 - 0.561score
authz-boundary-review
Mesteriis
Reviews authorization, tenant isolation, roles, ownership, row access, admin boundaries, sharing, and privilege escalation.
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get agent-retrospective running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
agent-retrospective skill. Agent Mart. https://agentmart.dev/skills/mesteriis-agent-retrospective (last updated 2026-10-24)