Run any Skill in Manus with one click

tx-docs-specs

Stars1

Forks0

UpdatedApril 20, 2026 at 16:14

Create, patch, lint, discover, trace, and complete docs-first specs. Use when working in Codex and the user needs tx commands from this area.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

jamesaphoenix

jamesaphoenix/tx-agent-kit

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

File Explorer

2 files

SKILL.md

readonly

name	tx-docs-specs
description	Create, patch, lint, discover, trace, and complete docs-first specs. Use when working in Codex and the user needs tx commands from this area.
metadata	{"short-description":"Create, patch, lint, discover, trace, and complete docs-first specs."}

tx Docs And Specs

Use when the user is working in PRDs, DDs, invariants, decision tracking, or markdown export flows.

Quick Start

tx doc add prd <name> --title "Title"
tx spec discover
tx spec status

Included Commands

tx decision: Manage decisions as first-class artifacts
tx decompose: Create a task graph from a design spec
tx doc: Manage docs-as-primitives
tx doc add: Create a new doc
tx doc attach: Attach a doc to a task
tx doc edit: Open doc markdown in editor
tx doc link: Link two docs
tx doc list: List all docs
tx doc lock: Lock a doc version
tx doc patch: Create a design patch doc
tx doc rm: Remove latest mutable doc version
tx doc rm: Remove latest mutable doc version
tx doc show: Show doc details
tx doc sync: Re-read docs from disk and update DB hashes
tx doc validate: Validate doc/task coverage and index search metadata
tx doc version: Create new version from locked doc
tx invariant is deprecated. Use 'tx spec' instead.
tx md-export: Export tasks to markdown file
tx spec: Docs-first spec-to-test traceability primitives
tx spec batch: Import test run results from stdin
tx spec complete: Record human completion sign-off
tx spec discover: Refresh doc-derived invariants and upsert test mappings
tx spec fci: Compute Feature Completion Index
tx spec gaps: List uncovered invariants (no linked tests)
tx spec health: Repo-level spec-driven development rollup
tx spec link: Manually link an invariant to a test
tx spec lint: All-in-one spec and doc checker
tx spec matrix: Full invariant-to-test traceability matrix
tx spec run: Record a pass/fail run result for a canonical test ID
tx spec status: Explain scope closure state
tx spec tests: List tests linked to an invariant
tx spec unlink: Remove an invariant/test mapping
tx triangle is a deprecated alias for 'tx spec health'.

Full Help

Read references/commands.md for the full generated CLI help text for this skill's commands.

Search And Shell Fixes

When working in Codex, prefer rg -n <pattern> <path> and rg --files <path> over broad grep -r or fragile find pipelines.

If a shell/search command fails because of malformed flags, truncated paths, or broken quotes:

rerun it as a smaller rg command with an explicit directory
avoid partial paths like node_modul or unterminated quotes
replace grep -r with rg -n unless rg is unavailable
replace broad find probes with rg --files when you are really locating source files

More from this repository

same repository

adversarial-bug-hunt

jamesaphoenix/tx-agent-kit

Long-running (multi-hour) adversarial hunt for P0/P1/P2 bugs across the codebase. Mixes codebase observation, mechanical linting, real test + telemetry verification, and parallel skeptic sub-agents that must REFUTE each candidate before it is accepted. Fixes verified bugs on a branch off main with surgical per-bug commits, re-runs gates, and writes a dated report to the Desktop. Never pushes or merges. Use when you want a deep, autonomous bug-finding-and-fixing pass.

2026-06-211

fix-test-flake

jamesaphoenix/tx-agent-kit

Diagnose and durably eliminate flaky/intermittent test failures (passes locally but fails CI, rotates between tests, red only under load). Reproduce under contention, instrument the real state instead of guessing, root-cause by signal not duration, fix at the source, validate multi-run. Use when a test is flaky, CI is intermittently red, or fixing one flake unmasks others.

2026-06-211

prune-dead-branches

jamesaphoenix/tx-agent-kit

Safely prune dead local branches, git worktrees, and remote branches in this repo. Use when asked to "prune dead branches", "clean up worktrees", "delete merged branches", "tidy up git", or after a batch of PRs has merged. Knows this repo merges via squash, so it verifies death by PR state, not just git ancestry.

2026-06-211

speed-up-test-suite

jamesaphoenix/tx-agent-kit

Reduce test-suite wall-clock (dev + CI) without losing coverage or telemetry. Measure the phase breakdown first, then apply proven levers (parallelize turbo, narrow imports vs barrels, lazy-load heavy graphs, pool/worker config, DB pool sizing) and capture the before/after delta. Use when tests are slow, CI time is high, or to set/check a perf baseline. Composes with the read-only test-perf and test-census skills.

2026-06-211

test-census

jamesaphoenix/tx-agent-kit

Census the repo's tests by TYPE, not by name. Classifies every tracked test file via content heuristics into unit / integration / react-component / e2e (plus a separate db pgTAP count), in precedence order so buckets are mutually exclusive. Use when the user asks "what kinds of tests do we have", "how many component vs integration tests", "what's our e2e coverage", or wants a per-area test-type breakdown.

2026-06-211

test-perf

jamesaphoenix/tx-agent-kit

Snapshot test-suite timings in this repo. Runs the unit and/or integration suites (or a single integration project) and reports wall-clock time, Vitest's own phase breakdown (transform/setup/import/tests/environment), and the slowest test files. Use when the user asks "how slow are the tests", "where does the test time go", wants a perf baseline, or wants to check the suite hasn't regressed.

2026-06-211

tx Docs And Specs

Use when the user is working in PRDs, DDs, invariants, decision tracking, or markdown export flows.

Quick Start

tx doc add prd <name> --title "Title"

tx spec discover

tx spec status

Included Commands

tx decision: Manage decisions as first-class artifacts

tx decompose: Create a task graph from a design spec

tx doc: Manage docs-as-primitives

tx doc add: Create a new doc

tx doc attach: Attach a doc to a task

tx doc edit: Open doc markdown in editor

tx doc link: Link two docs

tx doc list: List all docs

tx doc lock: Lock a doc version

tx doc patch: Create a design patch doc

tx doc rm: Remove latest mutable doc version

tx doc show: Show doc details

tx doc sync: Re-read docs from disk and update DB hashes

tx doc validate: Validate doc/task coverage and index search metadata

tx doc version: Create new version from locked doc

tx invariant is deprecated. Use 'tx spec' instead.

tx md-export: Export tasks to markdown file

tx spec: Docs-first spec-to-test traceability primitives

tx spec batch: Import test run results from stdin

tx spec complete: Record human completion sign-off

tx spec discover: Refresh doc-derived invariants and upsert test mappings

tx spec fci: Compute Feature Completion Index

tx spec gaps: List uncovered invariants (no linked tests)

tx spec health: Repo-level spec-driven development rollup

tx spec link: Manually link an invariant to a test

tx spec lint: All-in-one spec and doc checker

tx spec matrix: Full invariant-to-test traceability matrix

tx spec run: Record a pass/fail run result for a canonical test ID

tx spec status: Explain scope closure state

tx spec tests: List tests linked to an invariant

tx spec unlink: Remove an invariant/test mapping

tx triangle is a deprecated alias for 'tx spec health'.

Full Help

Read references/commands.md for the full generated CLI help text for this skill's commands.

Search And Shell Fixes

When working in Codex, prefer rg -n <pattern> <path> and rg --files <path> over broad grep -r or fragile find pipelines.

If a shell/search command fails because of malformed flags, truncated paths, or broken quotes:

rerun it as a smaller rg command with an explicit directory

avoid partial paths like node_modul or unterminated quotes

replace grep -r with rg -n unless rg is unavailable

replace broad find probes with rg --files when you are really locating source files