Install the "dox-describe" agent skill from https://github.com/BlackBeltTechnology/pi-agent-dashboard/tree/develop/packages/kb-extension/.pi/skills/dox-describe into .claude/skills/dox-describe/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dox-describe", then confirm the skill loads.
Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
skills CLI
$ npx skills add BlackBeltTechnology/pi-agent-dashboard --skill dox-describe -a codex
Project install goes to .agents/skills/; add -g for ~/.codex/skills/.
Install the "dox-describe" agent skill from https://github.com/BlackBeltTechnology/pi-agent-dashboard/tree/develop/packages/kb-extension/.pi/skills/dox-describe into .agents/skills/dox-describe/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dox-describe", then confirm the skill loads.
Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add BlackBeltTechnology/pi-agent-dashboard --skill dox-describe -a cursor
Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.
Install the "dox-describe" agent skill from https://github.com/BlackBeltTechnology/pi-agent-dashboard/tree/develop/packages/kb-extension/.pi/skills/dox-describe into .cursor/skills/dox-describe/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dox-describe", then confirm the skill loads.
Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
skills CLI
$ npx skills add BlackBeltTechnology/pi-agent-dashboard --skill dox-describe -a gemini-cli
Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.
Install the "dox-describe" agent skill from https://github.com/BlackBeltTechnology/pi-agent-dashboard/tree/develop/packages/kb-extension/.pi/skills/dox-describe into .gemini/skills/dox-describe/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dox-describe", then confirm the skill loads.
Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
skills CLI
$ npx skills add BlackBeltTechnology/pi-agent-dashboard --skill dox-describe -a github-copilot
Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.
Install the "dox-describe" agent skill from https://github.com/BlackBeltTechnology/pi-agent-dashboard/tree/develop/packages/kb-extension/.pi/skills/dox-describe into .github/skills/dox-describe/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dox-describe", then confirm the skill loads.
GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add BlackBeltTechnology/pi-agent-dashboard --skill dox-describe -a opencode
OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
Install the "dox-describe" agent skill from https://github.com/BlackBeltTechnology/pi-agent-dashboard/tree/develop/packages/kb-extension/.pi/skills/dox-describe into .opencode/skills/dox-describe/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dox-describe", then confirm the skill loads.
OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
Skill name
dox-describe
GitHub stars
315
Token cost
~1.3k tokens
SKILL.md length
721 words
Files
1
Skills in repo
70
Repo updated
First seen
Licence
MIT
At a glance
Fill the empty Purpose cells of a directory AGENTS.md tree with one-line LLM summaries (one subagent per file, plan-then-confirm, cap 50 rows/run).
Works in 4 steps: enumerate the empty rows → present the plan and confirm → fan out ONE subagent per AGENTS.md → …
A path-only kb dox init tree
SKILL.md covers Step 1 — enumerate the empty…, Step 2 — present the plan and…, Step 3 — fan out ONE subagent… and Step 4 — verify, report, reindex, plus 2 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Dox Describe is an agent skill from BlackBeltTechnology/pi-agent-dashboard. Fill the empty Purpose cells of a directory AGENTS.md tree with one-line LLM summaries (one subagent per file, plan-then-confirm, cap 50 rows/run). Use for a path-only kb dox init tree, or when asked to "describe the tree", "fill AGENTS.md purposes", or "populate the kb corpus".
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Subagents and Agent instruction files. The repository describes itself as: Real-time web dashboard for pi coding-agent sessions. Multi-session view, live chat mirroring, integrated terminal, diff viewer, pi-flows execution, and mobile-first remote… The licence is MIT.
When your agent uses it
A path-only kb dox init tree
Asked to describe the tree
Fill AGENTS.md purposes
Populate the kb corpus
Example prompts
“describe the tree”
“fill AGENTS.md purposes”
“populate the kb corpus”
“/dox-describe”
Workflow steps
4 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 7a2d171. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Dox Describe loads about 1.3k tokens when it runs. Until then it costs about 74 tokens; SKILL.md has 721 words of instructions outside code blocks.
Always· name and description, kept in context so the agent knows when to use it
~74
When it runs· the whole SKILL.md, loaded when a task matches
~1.3k
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
Download SKILL.mdSave it as .claude/skills/dox-describe/SKILL.md (or your agent's skills folder).
name
dox-describe
description
Fill the empty Purpose cells of a directory `AGENTS.md` tree with one-line LLM summaries (one subagent per file, plan-then-confirm, cap 50 rows/run). Use for a path-only `kb dox init` tree, or when asked to "describe the tree", "fill AGENTS.md purposes", or "populate the kb corpus".
dox-describe
Turn a path-only directory AGENTS.md tree into a searchable kb corpus. A fresh
kb dox init tree carries rows shaped | `file.ts` | | — the Purpose cell is
empty, so the agents retrieval lane (the one file-lookup queries depend on)
finds nothing. This skill fills those cells with one-line, caveman-style
purposes, one subagent per AGENTS.md.
Read-only first: the CLI enumerates empty rows; the LLM only ever writes a
Purpose cell. The parent never edits an AGENTS.md itself, and a subagent edits
only the single file it was assigned.
Step 1 — enumerate the empty rows
bash
kb dox describe --list --json
Parse { groups: [{ agentsPath, subjects: string[] }], total }. Each group is
one AGENTS.md; each subject is a path whose Purpose cell is empty. Nothing to
do when total === 0 — say so and stop.
Step 2 — present the plan and confirm
Show the user, then WAIT (ask_user, confirm) for approval before any write:
number of AGENTS.md files (groups) and number of rows (total);
a rough cost estimate (≈ rows × one short file read, plus one subagent per
group; state it is a rough bound, not a promise);
the per-run cap: 50 rows. Rows beyond the cap are DEFERRED to a re-run
(the walk is empty-cells-only, so a re-run is resumable by construction);
any row whose subject file is missing or unreadable (report, do not assign).
Never start fan-out without an explicit yes.
Step 3 — fan out ONE subagent per AGENTS.md
Cap concurrency at 2 in flight (the extension schedules a debounced reindex
on every markdown write, and every subagent contends on the single SQLite index;
≤2 keeps SQLITE_BUSY recoverable — the parent's final reindex is
authoritative). Skip groups whose rows are entirely past the cap.
Spawn with an inline Agent label (write-capable, parent defaults) and
model: "@fast" — one-line summaries do not need the parent's model. Do NOT use
Explore — it is read-only and cannot fill cells.
Each subagent's task must include:
the absolute AGENTS.md path and its assigned subjects (cap 50 total across
all groups for this run);
must read every file it describes — never guess from the filename;
the row rules:
ONE line per row, exactly the schema | `file` | purpose |;
purpose ≤ 200 chars, caveman style: short declarative fragments, drop
articles/copulas, subject → verb → object;
name key exports / contracts / params verbatim (symbolName, paths, env
vars); concrete tokens over prose;
CONDENSE, never promote to a <File>.AGENTS.md sidecar — sidecar splitting
is the parent's/scripts/split-large-agents.mjs job;
edit ONLY its own AGENTS.md; do not touch any other file;
write the purpose into the EXISTING row (same line, same path cell) — do not
add, delete, or reorder rows;
a subject file that cannot be read (missing, binary, 0-byte) → leave its
Purpose cell EMPTY and report it back; never invent a purpose.
Show full SKILL.md (283 more words)Show less
Step 4 — verify, report, reindex
kb dox lint — must be clean. On a finding, hand it back to the subagent
that owns that AGENTS.md to repair or revert its OWN file (the parent never
edits a tree file). Re-run lint after the repair.
One final reindex so the new purposes are searchable:bash
kb index
(The extension's debounced reindex is best-effort under contention; this
explicit pass is authoritative.)
Report to the user: rows filled, rows deferred (cap), unreadable rows left
empty, and — when deferred > 0 — "run dox-describe again to fill the rest".
Re-running is idempotent: --list returns only rows still empty, so a second
run writes nothing when everything is filled.
Headless escape hatch
For very large trees (well past the 50-row cap), the plan-then-confirm loop is
boring to babysit. You may instead drive workers with parallel headless pi
processes (pi -p --model <fast-ref> "<task>", where <fast-ref> is the
fast role's provider/id from list_roles — the CLI takes no @role), one
per AGENTS.md, then run steps 4.1–4.3
yourself. This is an escape hatch, not the default: it skips the interactive
confirm, so the CALLER owns the cap and the kb dox lint gate.
Pitfalls
Do NOT let a subagent "improve" neighbouring cells or reformat the table — the
parent's --list walk and kb dox lint both depend on the exact row shape.
Do NOT fan out more than 2 at once — concurrent reindex writes can hit
SQLITE_BUSY.
A wrong-but-non-empty purpose is NOT revisited in v1 (no correctness oracle);
a --stale refresh mode is a follow-up. Read the file before describing it.
Never write a Purpose for a file you could not open — an empty cell is honest,
a guessed one is rot.
Dox Describe next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
Dox Describe compared with similar skills
Skill
Stars
Used in
Tokens
Auto-check
Licence
Repo updated
Dox Describe this skillBlackBeltTechnology/pi-agent-dashboard
Designs a project-specific agent harness: defines specialist agents, writes the skills they follow, picks an execution mode and model for each, and keeps the setup maintained.
Scans installed skills for principles that recur across them and proposes rule-file changes: append, revise, add a section, create a file or leave as covered.
Reference for writing Claude Code agent files: location, frontmatter fields, validation limits, tool and model choices, and the required content format.
Diagnose failed GitHub Actions runs for pi-agent-dashboard: the 11-file workflow taxonomy, affected-test selection, the release pipeline, known failure modes, and how to read gh run logs and…
Disciplined implementation in pi-agent-dashboard: the rebuild matrix (extension→reload, server→restart, client→build+restart, openspec-apply→full rebuild) plus the project's code discipline rules.
Turn a pi session into a Markdown "how-we-did-it" collaboration guideline: reads the session's JSONL transcript and synthesizes a reusable playbook of which prompts worked, what had to be steered…
Fill the empty Purpose cells of a directory AGENTS.md tree with one-line LLM summaries (one subagent per file, plan-then-confirm, cap 50 rows/run). Dox Describe is an agent skill from BlackBeltTechnology/pi-agent-dashboard.md tree with one-line LLM summaries (one subagent per file, plan-then-confirm, cap 50 rows/run).
When should I use Dox Describe?
Dox Describe fits situations like: A path-only kb dox init tree; asked to describe the tree; fill AGENTS.md purposes; populate the kb corpus.
How do I install Dox Describe in Claude Code?
Run `npx skills add BlackBeltTechnology/pi-agent-dashboard --skill dox-describe -a claude-code`. Or copy the skill folder (packages/kb-extension/.pi/skills/dox-describe in BlackBeltTechnology/pi-agent-dashboard) into .claude/skills/dox-describe in your project. Claude Code loads it when a task matches its description.
How do I install Dox Describe in Codex?
Run `npx skills add BlackBeltTechnology/pi-agent-dashboard --skill dox-describe -a codex`. Or copy the skill folder (packages/kb-extension/.pi/skills/dox-describe in BlackBeltTechnology/pi-agent-dashboard) into .agents/skills/dox-describe in your project. Codex loads it when a task matches its description.
Can I use Dox Describe in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add BlackBeltTechnology/pi-agent-dashboard --skill dox-describe -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dox-describe, .gemini/skills/dox-describe, .github/skills/dox-describe and .opencode/skills/dox-describe in your project.
What does Dox Describe need to run?
SKILL.md names no scripts, command-line tools or credentials: Dox Describe is instructions for the agent only.
Does Dox Describe access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Dox Describe safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Dox Describe use?
Dox Describe is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Dox Describe use?
About 1.3k tokens (SKILL.md is roughly 5.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Dox Describe?
Skills that share tags, products or a category with Dox Describe: Task Observer (rebelytics/one-skill-to-rule-them-all, 3.2k stars), Harness Agent Team Designer (revfactory/harness, 9.1k stars), Repo Task Proof Loop (DenisSergeevitch/repo-task-proof-loop, 730 stars) and Rules Distillation (affaan-m/ECC, 277k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Dox Describe?
BlackBeltTechnology (a GitHub organization) maintains it in BlackBeltTechnology/pi-agent-dashboard, which has 315 GitHub stars. The repository holds 70 skills in this directory. The repository was last updated on October 10, 2026.
