starter-session-audit
Simple end-of-session audit that scans for uncaptured corrections, preferences, and decisions, then proposes saving them to the right workspace file.
Skill by hugobernardo
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/hugobernardo-starter-session-audit
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: security
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/starter-session-audit
What's inside
- Skill name
starter-session-audit- Description
- Simple end-of-session audit that scans for uncaptured corrections, preferences, and decisions, then proposes saving them to the right workspace file. Use this skill whenever you say 'audit this session,' 'session audit,' 'what did we miss,' or 'end of session check.' Works with any Cowork workspace that has a CLAUDE.md and MEMORY.md in the root folder.
- License
- MIT
- Instructions
- 91 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Starter Session Audit A lightweight audit that runs at the end of any Cowork session. It catches things you told Cowork during the session that should be saved permanently so you never have to say them again. ## What This Skill Does Two things, and only two things: 1. **Scans for uncaptured learnings.** Looks through the conversation for corrections you made, preferences you expressed, and decisions you stated that aren't already written in your workspace files. 2. **Proposes where to save each finding.** For each uncaptured learning, it tells you which file it belongs in, what section, and the exact wording. You approve or skip each one. That's it. No file reorganization, no cleanup, no progress tracking. Just: "Did I learn anything this session that should be remembered?" ## Step 1: Discover Your Workspace Find your workspace root dynamically. Look for a CLAUDE.md file in the mounted workspace folder. Read whatever workspace files exist. The audit adapts to your setup — it works whether you have one workstation or twenty. Read these files if they exist: 1. Root CLAUDE.md (your standing instructions) 2. Root MEMORY.md (your accumulated context) 3. Any workstation CLAUDE.md and MEMORY.md files that were used during this session 4. Any project CLAUDE.md and MEMORY.md files that were used during this session 5. Any reference files that were loaded during this session (e.g., voice-principles.md) ## Step 2: Scan the Conversation Go through the entire conversation from top to bottom. Look for these four signal types: ### A. Corrections You fixed something Cowork produced. Maybe you changed a word, rewrote a sentence, adjusted a format, or said "no, do it this way instead." Each correction reveals a rule that Cowork should follow next time. **What to look for:** Moments where you edited, rejected, or rewrote Cowork's output. Ask: what underlying preference or rule drove the change? **Example:** You changed "Best regards" to "Thanks" on an email draft. The underlying rule: "Sign off with 'Thanks' for internal contacts." ### B. Explicit Preferences You stated a preference directly. Words like "always," "never," "I prefer," "from now on," "I like it when," or "don't do that." **What to look for:** Direct instructions about how you want things done, even casual ones. **Example:** "I prefer bullet points over numbered lists." "Don't use exclamation points in subject lines." ### C. Decisions You made a decision that affects future work. Chose one option over another, set a deadline, established a rule for a project, or resolved an ambiguity. **What to look for:** Choices that should be recorded so Cowork doesn't re-ask the same question later. **Example:** "Let's go with the $5,000 savings target." "Cancel the gym membership, keep Spotify." ### D. New Context You shared a fact about yourself, your work, or your world that Cowork didn't previously know. Contact details, schedules, relationships, project updates, or anything that changes how Cowork should approach future tasks. **What to look for:** Information that would help Cowork in a future session if it remembered it. **Example:** "My rent went up to $2,600 starting next month." "Sarah is my new manager." ## Step 3: Filter Against What's Already Saved For each finding from Step 2, check whether it's already captured in the workspace files you loaded in Step 1. Skip anything that's already written down. Only surface genuinely new findings. ## Step 4: Present Findings Present each finding in this format: ``` **[Number]. [What happened]** - **The rule/fact:** [Exact wording to save, written as a clear instruction or statement] - **Where it goes:** [File path and section name] - **Why:** [One sentence on why this matters for future sessions] ``` Group findings into two categories: **Recommend (apply unless you object):** Clear-cut findings where the right action is obvious. **Your call:** Findings where there's a judgment call or where you might want to phrase the rule differently. If there are no findings, say so: "Clean session. Nothing new to capture." Don't manufacture findings. ## Step 5: Apply Approved Changes After you approve (all, some, or none), write the approved changes to the appropriate files. For each change, confirm what was written and where. **Important:** Never write changes without approval. Always present findings first and wait.
From hugobernardo/skills-library, MIT.
More from hugobernardo/skills-library
- 0.565score
red-team-analyst
hugobernardo
Stress-test reports, plans, ideas, and work with evidence-based red-team analysis, then conduct a rational, one-question-at-a-time debate; use when the user…
SkillAFreshness: AClaude Code +9 - 0.529score
tam-analysis
hugobernardo
Research, size, validate and govern the market for a product — TAM/SAM/SOM built to a skeptical-investor standard: graded evidence, explicit ranges, no double…
SkillBFreshness: BClaude Code +9 - 0.529score
website-audit
hugobernardo
Run the client website audit, an end-to-end SEO plus AEO/GEO review of a company site that ends in a six-section report delivered as markdown and .docx, plus…
SkillBFreshness: BClaude Code +9 - 0.529score
creative-exploration
hugobernardo
Turn a small seed into unusually diverse, original, and useful creative possibilities through interactive territory mapping, anti-anchoring, distant…
SkillBFreshness: BClaude Code +9 - 0.529score
idea-to-prd
hugobernardo
Run a product idea through the governed Product OS from discovery to a decision-ready, buildable PRD.
SkillBFreshness: BClaude Code +9 - 0.529score
idea-validation
hugobernardo
Generate and validate a broad field of interactive marketing utilities and software-as-marketing concepts through territory mapping, operational constraints…
SkillBFreshness: BClaude Code +9 - 0.529score
presentation-builder
hugobernardo
Build any presentation — sales pitch, investor deck, board update, conference talk, internal readout, training session, QBR — through a staged process that…
SkillBFreshness: BClaude Code +9 - 0.529score
prompt-optimizer
hugobernardo
Select the best prompt architecture for a concrete outcome and produce one fully written, ready-to-use prompt.
SkillBFreshness: BClaude Code +9 - 0.524score
keep-it-simple
hugobernardo
Switch to plain, low-effort-to-read language when Hugo directly asks for it — "keep it simple," "ELI5," "simple mode," "talk to me like I'm 5,"…
SkillBFreshness: BClaude Code +9 - 0.524score
create-content-plan
hugobernardo
Generate comprehensive content marketing strategy with editorial calendar, content pillars, and distribution plans.
SkillBFreshness: BClaude Code +9 - 0.524score
create-gtm-strategy
hugobernardo
Build a go-to-market strategy as a working document — clarify the situation, draft with labeled evidence, audit it for internal contradictions, and convert it…
SkillBFreshness: BClaude Code +9 - 0.524score
angle-finder
hugobernardo
Research a topic and produce the ingredients for ONE deep post on it — a single sharp angle, hooks, pro/con arguments, key stats, notable quotes, a story…
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 2, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/hugobernardo/skills-library
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from hugobernardo
- 0.565score
red-team-analyst
hugobernardo
Stress-test reports, plans, ideas, and work with evidence-based red-team analysis, then conduct a rational, one-question-at-a-time debate; use when the user…
SkillAFreshness: AClaude Code +9 - 0.529score
prompt-optimizer
hugobernardo
Select the best prompt architecture for a concrete outcome and produce one fully written, ready-to-use prompt.
SkillBFreshness: BClaude Code +9 - 0.529score
creative-exploration
hugobernardo
Turn a small seed into unusually diverse, original, and useful creative possibilities through interactive territory mapping, anti-anchoring, distant…
SkillBFreshness: BClaude Code +9 - 0.529score
idea-to-prd
hugobernardo
Run a product idea through the governed Product OS from discovery to a decision-ready, buildable PRD.
SkillBFreshness: BClaude Code +9 - 0.529score
idea-validation
hugobernardo
Generate and validate a broad field of interactive marketing utilities and software-as-marketing concepts through territory mapping, operational constraints…
SkillBFreshness: BClaude Code +9 - 0.529score
presentation-builder
hugobernardo
Build any presentation — sales pitch, investor deck, board update, conference talk, internal readout, training session, QBR — through a staged process that…
SkillBFreshness: BClaude Code +9
Cite this page
starter-session-audit skill. Agent Mart. https://agentmart.dev/skills/hugobernardo-starter-session-audit (last updated 2026-10-24)