Run any Skill in Manus with one click

aidd-docio

Stars5

Forks0

UpdatedApril 21, 2026 at 04:23

Owns shared DocIO runtime for markdown slicing/patching, actions validation/apply, and context-map expansion. Use when stage skills need canonical DocIO operations. Do not use when the request primarily belongs to `aidd-flow-state` lifecycle updates or `aidd-core` ownership routing.

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

GrinRus

GrinRus/ai_driven_dev

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

9 files

SKILL.md

readonly

name	aidd-docio
description	Owns shared DocIO runtime for markdown slicing/patching, actions validation/apply, and context-map expansion. Use when stage skills need canonical DocIO operations. Do not use when the request primarily belongs to `aidd-flow-state` lifecycle updates or `aidd-core` ownership routing.
lang	en
model	inherit
user-invocable	false

Scope

This skill owns shared DocIO runtime entrypoints.
Stage skills consume these APIs for preflight/postflight and deterministic document updates.
Flow-state orchestration remains in feature-dev-aidd:aidd-core and feature-dev-aidd:aidd-loop.

Canonical shared Python entrypoints

python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-docio/runtime/md_slice.py
python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-docio/runtime/md_patch.py
python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-docio/runtime/actions_validate.py
python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-docio/runtime/actions_apply.py
python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-docio/runtime/context_map_validate.py
python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-docio/runtime/context_expand.py

Command contracts

`python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-docio/runtime/md_slice.py`

When to run: when stage or subagent needs bounded section reads instead of full-file scans.
Inputs: source markdown path with heading/line selectors.
Outputs: deterministic excerpt payload for pack-first evidence workflows.
Failure mode: non-zero exit on missing file, invalid selectors, or malformed markdown boundaries.
Next action: fix selectors/source path and rerun the same slice command.

`python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-docio/runtime/actions_apply.py`

When to run: stage-chain postflight after validated *.actions.json is available.
Inputs: --actions <path> with optional apply-log paths and stage context.
Outputs: applied updates, progress synchronization, and downstream stage artifacts.
Failure mode: non-zero exit on schema violations, write failures, or boundary guard blocks.
Next action: inspect apply log, fix action payload/root cause, then rerun stage-chain postflight.

Ownership guard

DocIO-facing runtime modules must be implemented under skills/aidd-docio/runtime/*.
Consumers should reference skills/aidd-docio/runtime/* as canonical paths.

Additional resources

references/read-write-maps.md (when: readmap/writemap behavior is in question; why: align map validation and expansion semantics).
references/actions-flow.md (when: actions schema/apply behavior is unclear; why: follow validator-to-apply lifecycle).

More from this repository

same repository

aidd-core

GrinRus/ai_driven_dev

Aggregates shared runtime navigation and cross-skill ownership links. Use when resolving shared runtime entrypoints or ownership boundaries. Do not use when the request belongs to `aidd-policy` output/question rules or `status` summary reporting.

2026-04-215

aidd-flow-state

GrinRus/ai_driven_dev

Owns shared flow/state runtime for stage state, progress/tasklist, and stage-result lifecycle. Use when orchestration needs canonical active-stage, progress, tasklist, or stage-result commands. Do not use when the request is about `aidd-docio` action patch mechanics or `status` read-only summaries.

2026-04-215

aidd-init

GrinRus/ai_driven_dev

Initializes AIDD workspace scaffolding for the current project. Use when bootstrapping canonical `aidd/` templates and project-owned test execution contract in `aidd/config/gates.json`. Do not use when the request is to start feature ideation (`idea-new`) or to inspect existing ticket progress (`status`).

2026-04-215

aidd-loop

GrinRus/ai_driven_dev

Enforces loop-mode discipline for implement/review/qa (packs, scope, no questions). Use when loop stages require bounded scope and retry policy. Do not use when direct stage execution belongs to `implement`, `review`, or `qa` stage skills.

2026-04-215

aidd-observability

GrinRus/ai_driven_dev

Owns shared observability/runtime reporting for diagnostics, inventory, identifiers, logs, and DAG export. Use when deterministic diagnostics or inventory exports are required. Do not use when request scope is `status` stage summaries or `aidd-core` runtime ownership mapping.

2026-04-215

aidd-rlm

GrinRus/ai_driven_dev

Owns shared RLM evidence workflow for subagents (slice, build, verify, finalize, pack). Use when preload roles require canonical RLM evidence operations. Do not use when the request is stage-local research execution in `researcher` or stage handoff-only guidance in `aidd-stage-research`.

2026-04-215

name	aidd-docio
description	Owns shared DocIO runtime for markdown slicing/patching, actions validation/apply, and context-map expansion. Use when stage skills need canonical DocIO operations. Do not use when the request primarily belongs to `aidd-flow-state` lifecycle updates or `aidd-core` ownership routing.
lang	en
model	inherit
user-invocable	false

Scope

This skill owns shared DocIO runtime entrypoints.
Stage skills consume these APIs for preflight/postflight and deterministic document updates.
Flow-state orchestration remains in feature-dev-aidd:aidd-core and feature-dev-aidd:aidd-loop.

Canonical shared Python entrypoints

python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-docio/runtime/md_slice.py
python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-docio/runtime/md_patch.py
python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-docio/runtime/actions_validate.py
python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-docio/runtime/actions_apply.py
python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-docio/runtime/context_map_validate.py
python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-docio/runtime/context_expand.py

Command contracts

`python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-docio/runtime/md_slice.py`

When to run: when stage or subagent needs bounded section reads instead of full-file scans.
Inputs: source markdown path with heading/line selectors.
Outputs: deterministic excerpt payload for pack-first evidence workflows.
Failure mode: non-zero exit on missing file, invalid selectors, or malformed markdown boundaries.
Next action: fix selectors/source path and rerun the same slice command.

`python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-docio/runtime/actions_apply.py`

When to run: stage-chain postflight after validated *.actions.json is available.
Inputs: --actions <path> with optional apply-log paths and stage context.
Outputs: applied updates, progress synchronization, and downstream stage artifacts.
Failure mode: non-zero exit on schema violations, write failures, or boundary guard blocks.
Next action: inspect apply log, fix action payload/root cause, then rerun stage-chain postflight.

Ownership guard

DocIO-facing runtime modules must be implemented under skills/aidd-docio/runtime/*.
Consumers should reference skills/aidd-docio/runtime/* as canonical paths.

Additional resources

references/read-write-maps.md (when: readmap/writemap behavior is in question; why: align map validation and expansion semantics).
references/actions-flow.md (when: actions schema/apply behavior is unclear; why: follow validator-to-apply lifecycle).