Skip to content
Agentmart
Submit a tool

confluence-publish

Use to write findings, runbooks, or work documentation to Confluence.

Skill by agentchieflou

IndexedMIT★ 1
Write a review

Chalk Labs

Need help deploying confluence-publish?

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.

Book a call

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/agentchieflou-confluence-publish

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.

We use your email only for this newsletter. Privacy

About

Use to write findings, runbooks, or work documentation to Confluence. Use after UAT findings exist, after a deploy, or when the user asks to document work. Deterministic extraction first, one narrow model pass, scripted publish.

Use cases: documents, devops, writing

No 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/confluence-publish

What's inside

Skill name
confluence-publish
Description
Use to write findings, runbooks, or work documentation to Confluence. Use after UAT findings exist, after a deploy, or when the user asks to document work. Deterministic extraction first, one narrow model pass, scripted publish.
License
MIT
Instructions
20 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Confluence publish

`ad-confluence publish` builds the page from Markdown and runs toil's `confluence page create|update` behind the
approval gate; `ad-doctor` rows `toil / toil launcher` and `toil / confluence connection` must not be `fail`. Confluence does not render Markdown: you never write the page body yourself.

1. Source of truth is a Markdown file under `.agent/out/` (e.g. `<KEY>-uat-findings.md`). No file → go back to the skill that produced the data. Do not compose from memory.
2. Space + parent come from `AGENTS.md` (`confluence_space`, `confluence_parent`). Missing → `friction-log` type `missing-info`. STOP.
3. Write the page source to `.agent/out/<KEY>-confluence.md` (the wrap-up republishes from that file). Missing sections (`Context`, `Method`, `Findings`, `Recommendation`, `Artifacts` with the `path`s) → add them **to that Markdown file**, ≤ 60 lines total. Never hand-write HTML: `ad-confluence publish` refuses a source that is not Markdown.
4. Dry run:

```
ad-confluence publish .agent/out/<KEY>-confluence.md --dry-run
```

   The title is the file's first `#` heading (`--title "<KEY> — <summary>"` overrides it); the page this ticket already has (`state.confluence_url`) → add `--overwrite <page id>`. The body goes to toil on stdin; never put it on a command line yourself.
5. Read `"ok"`, then `action`, `title`, `space`, `parent`, `warnings`. `refused: writes_off`, `no_connection` or `toil_not_ready` → toil cannot write the page yet, a person's setup in toil: print `hint` verbatim, `friction-log` type `missing-info`, STOP. Any other `false` → print `meta.hint`, fix the source, retry once. Second failure → `friction-log` type `tool-error`. STOP.
6. Re-run without `--dry-run`. Capture `url` from the result. `refused: approval_timeout` or `approval_denied` → `friction-log` type `missing-info` quoting the `approval` id and the `hint`. Do not retry.
7. Comment on Jira: `ad-jira comment <KEY> --body "Documented: <URL>" --dry-run`, read `"ok"`, then run the same without `--dry-run`. `refused: approval_timeout` or `approval_denied` → as step 6.
8. `state-update`: `confluence_url`, `phase=documenting`. Hand off → `bitbucket-pr` if code changed, else `router`.

From agentchieflou/this-next-please, MIT.

More from agentchieflou/this-next-please

Signals

Stars
1
Forks
0
Open issues
61
Last commit (this folder)
Oct 21, 2026 (9 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from agentchieflou

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 confluence-publish 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.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying confluence-publish?

CallGet help
Cite this page

confluence-publish skill. Agent Mart. https://agentmart.dev/skills/agentchieflou-confluence-publish (last updated 2026-10-24)