Chalk Labs
Need help deploying ai-brag-document?
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/cristiano-pacheco-ai-brag-document
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: documents
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/ai-brag-document
What's inside
- Skill name
ai-brag-document- Description
- Engineering brag document
- License
- MIT
- Instructions
- 728 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- body: 728 lines (spec recommends under 500)
Files (1)
- SKILL.md
SKILL.md (first lines)
# AI Brag Document
Create a concise, evidence-based record of engineering impact that is useful for performance reviews, promotion discussions, calibration, and career reflection.
The document must answer five questions quickly:
1. What changed?
2. Why did it matter?
3. What did the author personally own?
4. What evidence supports the claim?
5. Is the result confirmed, expected, targeted, or still in progress?
## Workflow
Follow these steps in order:
1. Determine the scope and reporting period.
2. Discover relevant work and supporting evidence.
3. Build an internal evidence ledger.
4. Group related work into impact narratives.
5. Write the executive summary.
6. Write the main impact sections.
7. Separate work in progress and unverified outcomes.
8. Add a technical evidence appendix.
9. Run the quality checks.
10. Write the result to `$OBSIDIAN_AI_VAULT/brag-document.md` (default `$HOME/Documents/obsidian/obsidian/brag-document.md`) and verify the persisted file.
11. Ensure `$OBSIDIAN_AI_VAULT/engineering/index.md` links to the brag document.
12. Stage only the generated files and delegate the commit to the `ai-commit` skill (it targets the vault repo, never the code repo).
## Obsidian vault I/O
The Obsidian vault is the mandatory source of truth for the brag document. Read the source notes directly from the filesystem and write the generated document directly back to the same vault.
The vault root resolves from `$OBSIDIAN_AI_VAULT` (defaults to `$HOME/Documents/obsidian/obsidian` if unset) — the same override point used by every `ai-*` skill. Always use these resolved paths:
```bash
VAULT_PATH="${OBSIDIAN_AI_VAULT:-$HOME/Documents/obsidian/obsidian}"
ENGINEERING_PATH="$VAULT_PATH/engineering"
ENGINEERING_INDEX="$ENGINEERING_PATH/index.md"
BRAG_DOCUMENT="$VAULT_PATH/brag-document.md"
```
### Verify the vault
```bash
VAULT_PATH="${OBSIDIAN_AI_VAULT:-$HOME/Documents/obsidian/obsidian}"
ENGINEERING_PATH="$VAULT_PATH/engineering"
ENGINEERING_INDEX="$ENGINEERING_PATH/index.md"
BRAG_DOCUMENT="$VAULT_PATH/brag-document.md"
test -d "$VAULT_PATH" || {
echo "Obsidian vault not found: $VAULT_PATH" >&2
exit 1
}
test -d "$ENGINEERING_PATH" || {
echo "Engineering vault tree not found: $ENGINEERING_PATH" >&2
exit 1
}
```
Stop when the fixed vault or its `engineering/` tree does not exist. The vault must also be a Git repository:
```bash
git -C "$VAULT_PATH" rev-parse --is-inside-work-tree >/dev/null || {
echo "Obsidian vault is not a Git repository: $VAULT_PATH" >&2
exit 1
}
```
Before changing files, inspect the repository state. Unrelated unstaged changes may remain, but the staging area must be empty so the brag-document commit cannot absorb another task:
```bash
git -C "$VAULT_PATH" status --short
if ! git -C "$VAULT_PATH" diff --cached --quiet; then
echo "The Obsidian vault already has staged changes. Commit or unstage them before running this skill." >&2
git -C "$VAULT_PATH" diff --cached --name-only >&2
exit 1
fi
```
### Discover source notes
Collect candidate evidence from the **entire Engineering tree** at `$OBSIDIAN_AI_VAULT/engineering` (default `$HOME/Documents/obsidian/obsidian/engineering`). This is mandatory. Do not limit discovery to repositories already mentioned by the user, the current brag document, recently edited notes, or the first matching workplan.
Search the whole Engineering tree in multiple passes. Complete every pass before deciding which accomplishments belong in the brag document.
#### Pass 1 — Inventory every Engineering note
Create a complete, sorted inventory of Markdown notes and inspect the directory structure:
```bash
find "$ENGINEERING_PATH" -type f -name '*.md' -print | sort
find "$ENGINEERING_PATH" -type d \( \
-iname 'workplan' -o \
-iname 'workplans' -o \
-iname 'projects' -o \
-iname 'incidents' -o \
-iname 'postmortems' \
\) -print | sort
```
Do not skip nested service, platform, shared-library, archived, or cross-team folders merely because their repository names are not known in advance.
#### Pass 2 — Find workplans and design artifacts
Search by both path/filename and content. Workplans often contain an `index.md` that links to the PRD, technical specification, alternatives, rollout notes, or implementation status.
```bash
find "$ENGINEERING_PATH" -type f -name '*.md' \( \
-ipath '*/workplans/*' -o \
-iname '*workplan*' -o \
-iname 'prd.md' -o \
-iname 'tech-spec.md' -o \
-iname 'tech-spec-*.md' -o \
-iname '*technical-spec*' -o \
-iname '*design*' -o \From cristiano-pacheco/ai-tools, MIT.
More from cristiano-pacheco/ai-tools
- 0.583score
ai-create-pr
cristiano-pacheco
Write a PR title and description.
SkillAFreshness: A★ 1Claude Code +9 - 0.583score
ai-full-code-review
cristiano-pacheco
Review a branch diff for production risk.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
ai-commit
cristiano-pacheco
Commit and push vault artifacts or explicitly scoped code changes.
SkillAFreshness: A★ 1Claude Code +9 - 0.562score
ai-code-review
cristiano-pacheco
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding…
SkillAFreshness: A★ 1Claude Code +9 - 0.556score
ai-implement
cristiano-pacheco
Implement a piece of work based on a spec or set of tickets.
SkillAFreshness: A★ 1Claude Code +9 - 0.552score
100-go-rules
cristiano-pacheco
Apply a compact, Go-version-aware rulebook derived from the 100 numbered mistakes cataloged by 100go.co when writing, reviewing, debugging, refactoring…
SkillBFreshness: B★ 1Claude Code +9 - 0.543score
ai-execute-task
cristiano-pacheco
Implement the next task from a list.
SkillBFreshness: B★ 1Claude Code +9 - 0.543score
ai-reindex
cristiano-pacheco
Rebuild Obsidian wikilink indexes.
SkillBFreshness: B★ 1Claude Code +9 - 0.543score
ai-create-techspec
cristiano-pacheco
Create a tech spec from a PRD.
SkillBFreshness: B★ 1Claude Code +9 - 0.543score
ai-execute-plan
cristiano-pacheco
Execute a technical implementation plan.
SkillBFreshness: B★ 1Claude Code +9 - 0.543score
ai-codebase-review
cristiano-pacheco
Audit a whole codebase for bottlenecks.
SkillBFreshness: B★ 1Claude Code +9 - 0.543score
ai-review-techspec
cristiano-pacheco
Review a tech spec as principal architect.
SkillBFreshness: B★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Aug 22, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/cristiano-pacheco/ai-tools
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from cristiano-pacheco
- 0.583score
ai-full-code-review
cristiano-pacheco
Review a branch diff for production risk.
SkillAFreshness: A★ 1Claude Code +9 - 0.583score
ai-create-pr
cristiano-pacheco
Write a PR title and description.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
ai-commit
cristiano-pacheco
Commit and push vault artifacts or explicitly scoped code changes.
SkillAFreshness: A★ 1Claude Code +9 - 0.562score
ai-code-review
cristiano-pacheco
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding…
SkillAFreshness: A★ 1Claude Code +9 - 0.556score
ai-implement
cristiano-pacheco
Implement a piece of work based on a spec or set of tickets.
SkillAFreshness: A★ 1Claude Code +9 - 0.552score
100-go-rules
cristiano-pacheco
Apply a compact, Go-version-aware rulebook derived from the 100 numbered mistakes cataloged by 100go.co when writing, reviewing, debugging, refactoring…
SkillBFreshness: B★ 1Claude 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 ai-brag-document 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
ai-brag-document skill. Agent Mart. https://agentmart.dev/skills/cristiano-pacheco-ai-brag-document (last updated 2026-10-24)