close-campaign
Close a re-discipline campaign: promote remaining findings, write the summary, archive the folder.
Skill by adiazpar
Chalk Labs
Need help deploying close-campaign?
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/adiazpar-close-campaign
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: writing, marketing
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/close-campaign
What's inside
- Skill name
close-campaign- Description
- Close a re-discipline campaign: promote remaining findings, write the summary, archive the folder. A file move, not a proof obligation.
- License
- MIT
- Instructions
- 26 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
CLI examples use `re-search`; on Windows use `re-search.exe`.
# Close A Campaign
1. **Final promotion sweep** over `active/<slug>/findings/`. For each
candidate, follow the [curation conventions](../curate/SKILL.md): atomic claim?
Knowledge complete without Evidence? evidence cited in Evidence? grade matches
evidence? Normalize older candidates to that format during promotion. Then:
- search `docs/` for duplicates (`re-search query`) and merge instead
of duplicating;
- conflicts: higher evidence grade wins, or record both with the
conflict noted;
- accept → set `status: promoted`, move into the right `docs/`
subfolder;
- reject → leave it in the campaign folder (it archives with the
campaign; nothing is destroyed).
2. Run `.re-discipline/bin/re-search index` (rebuilds the index and
regenerates `docs/INDEX.md`).
3. Optionally run `.re-discipline/bin/re-search bench` and add any
questions this campaign answered to `golden.jsonl`.
4. In `CAMPAIGN.md`: set `Status: closed`, add a short summary — what
was achieved, key promoted findings, dead ends worth remembering.
5. Move `active/<slug>/` to `archive/<slug>/`.
6. Show the user the git diff of promotions for review. Do not commit
unless asked.From adiazpar/re-discipline, MIT.
More from adiazpar/re-discipline
- 0.589score
community
adiazpar
Create, connect, and manage community knowledge bases, membership, invitations, access policies, and service sign-in through the re-discipline community tool.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
visualize
adiazpar
Draw this project's re-discipline knowledge base and the retrieval machine that searches it, as an interactive page traced from the live index.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
curate
adiazpar
The re-discipline curation conventions: how investigators (inline manager or subagents) write reports and distill candidate findings, and how managers promote…
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
init-project
adiazpar
Initialize or resync a re-discipline project.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
open-campaign
adiazpar
Open a re-discipline campaign: an investigation workspace for one task.
SkillAFreshness: A★ 1Claude Code +9 - 0.544score
publish
adiazpar
Publish selected portable claims through one preparation, review and transfer route; research and operational memory remain local.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
review
adiazpar
Review published claims, applicability and overlapping information through the community review queue, preserving authorship and revision history.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
sync
adiazpar
Synchronize explicitly connected community KBs into a separate offline cache, report freshness and access failures, and control local/external retrieval.
SkillBFreshness: B★ 1Claude Code +9 - 0.539score
dashboard
adiazpar
Open the optional community web interface for visual review, publication, membership, and policy management while keeping agent commands available.
SkillBFreshness: B★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 23, 2026 (6 days ago)
- Last release
- Sep 8, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/adiazpar/re-discipline
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from adiazpar
- 0.589score
community
adiazpar
Create, connect, and manage community knowledge bases, membership, invitations, access policies, and service sign-in through the re-discipline community tool.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
visualize
adiazpar
Draw this project's re-discipline knowledge base and the retrieval machine that searches it, as an interactive page traced from the live index.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
curate
adiazpar
The re-discipline curation conventions: how investigators (inline manager or subagents) write reports and distill candidate findings, and how managers promote…
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
init-project
adiazpar
Initialize or resync a re-discipline project.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
open-campaign
adiazpar
Open a re-discipline campaign: an investigation workspace for one task.
SkillAFreshness: A★ 1Claude Code +9 - 0.544score
publish
adiazpar
Publish selected portable claims through one preparation, review and transfer route; research and operational memory remain local.
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 close-campaign 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
close-campaign skill. Agent Mart. https://agentmart.dev/skills/adiazpar-close-campaign (last updated 2026-10-24)