@elvis1513/auto-coding-skill 3.0.0 → 3.0.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -1,17 +1,20 @@
1
1
  ---
2
2
  name: auto-coding-skill
3
- description: Generic .agents engineering workflow with isolated Git worktrees for parallel write tasks, adaptive micro/standard/high-risk profiles, minimal project scaffolding, safe integration and branch cleanup, and evidence-backed dev or verified closure.
3
+ description: Generic .agents engineering workflow with isolated Git worktrees for parallel write tasks, fast changed-scope local gates, push-based completion, required project access configuration, safe integration, and branch cleanup.
4
4
  ---
5
5
 
6
6
  # Auto Coding Skill
7
7
 
8
- Use this skill for a disciplined task → design → implementation → verification
9
- → closure workflow. The project keeps one manual configuration source:
8
+ Use this skill for an analysis → decomposition → design → development → fast
9
+ gate → push workflow. The project keeps one manual configuration source:
10
10
  `docs/ENGINEERING.md`.
11
11
 
12
12
  At task start, inventory installed skills, MCP servers, connectors, browser
13
13
  tools, and repository scripts. Prefer the most direct authoritative capability.
14
- Use subagents only when work is independent and the runtime supports them.
14
+ The main agent decomposes the task before dispatch. Run independent read-only
15
+ discovery roles in parallel when the runtime supports them. Assign each
16
+ independent write unit to exactly one fixer in its own registered worktree;
17
+ never share a write worktree between agents.
15
18
 
16
19
  ## Install and upgrade
17
20
 
@@ -36,50 +39,84 @@ python3 docs/tools/autopipeline/ap.py upgrade --write
36
39
 
37
40
  Upgrade preserves project documents, custom agents, and explicit local model
38
41
  overrides. Managed agents without a `model` inherit the current client model.
42
+ Initialization is incomplete until every URL, username, and direct password under
43
+ `access.*` is filled in `docs/ENGINEERING.md` and `doctor` passes.
39
44
 
40
45
  ## Configuration and profiles
41
46
 
42
47
  Read `docs/ENGINEERING.md` before choosing a path. `workflow.profile: auto`
43
48
  resolves to exactly one execution profile:
44
49
 
45
- - `micro`: docs/tests-only or isolated low-risk work; changed gate; dev closure.
46
- - `standard`: ordinary feature or defect work; standard gate; dev closure.
47
- - `high-risk`: DB, auth, payment, deployment/build configuration, declared full
48
- rules, or explicit verify work; real full gate; verify closure.
50
+ - `micro`: docs/tests-only or isolated low-risk work.
51
+ - `standard`: ordinary feature or defect work.
52
+ - `high-risk`: DB, auth, payment, deployment/build, or broad structural work.
49
53
 
50
- High-risk signals cannot be manually downgraded. A full gate must use
51
- `commands.gate_full` or `commands.full_gate`; light/standard fallbacks do not
52
- count. An explicit non-auto configured profile replaces auto's low/normal
53
- baseline but cannot suppress high-risk signals. CI/Jenkins and target
54
- verification remain controlled by `verification.*_required`.
54
+ Use profiles only to adjust analysis, design depth, and reviewer recommendations.
55
+ Run exactly one changed-scope fast local gate for every profile. Keep standard/full
56
+ regression, structure scans, Docker, API verification, Jenkins, deployment, and
57
+ target checks as explicit diagnostics outside the default development flow.
55
58
 
56
- Run:
59
+ Run the configuration and impact preflight:
57
60
 
58
61
  ```bash
59
62
  python3 docs/tools/autopipeline/ap.py doctor
60
63
  python3 docs/tools/autopipeline/ap.py classify --scope auto
61
- python3 docs/tools/autopipeline/ap.py light-gate --scope auto --explain
64
+ # Before development, add repeatable --planned-path values and either --intent
65
+ # or --intent-file when the working tree does not yet describe the task.
62
66
  ```
63
67
 
68
+ `light-gate` remains available for an explicit gate-diagnostic task. Do not run
69
+ it before normal `commit-push`; `commit-push` owns the single automatic gate.
70
+
64
71
  ## Parallel write isolation
65
72
 
66
73
  Every task that may write files must use its own registered Git worktree and
67
- task branch. Read-only discovery may stay in the primary worktree.
74
+ task branch. Read-only discovery may stay in the primary worktree. A registered
75
+ worktree has exactly one writer. The main agent and other fixers must not edit it
76
+ while its owning fixer is active.
68
77
 
69
78
  ```bash
70
- python3 docs/tools/autopipeline/ap.py task-start <TASK_ID>
79
+ python3 docs/tools/autopipeline/ap.py task-start <TASK_ID> \
80
+ --owned-path <PATH> --depends-on <TASK_ID=SHA> --writer <WRITER>
71
81
  # Continue in the worktree path printed by task-start.
72
82
  python3 docs/tools/autopipeline/ap.py task-status <TASK_ID>
73
83
  python3 docs/tools/autopipeline/ap.py task-submodule-sync <TASK_ID>
74
- python3 docs/tools/autopipeline/ap.py commit-push <TASK_ID> --msg "<TASK_ID>: <summary>"
84
+ python3 docs/tools/autopipeline/ap.py task-review <TASK_ID> \
85
+ --verdict approved --diff-fingerprint <SHA256> --reviewer <REVIEWER>
86
+ python3 docs/tools/autopipeline/ap.py task-handoff <TASK_ID> \
87
+ --from <WRITER> --to <WRITER> [--generation <N>]
88
+ python3 docs/tools/autopipeline/ap.py commit-push <TASK_ID> \
89
+ --msg "<TASK_ID>: <summary>" [--writer <WRITER>]
75
90
  python3 docs/tools/autopipeline/ap.py task-integrate <TASK_ID>
91
+ # After resolving an integration rebase conflict:
92
+ python3 docs/tools/autopipeline/ap.py task-resume <TASK_ID>
76
93
  ```
77
94
 
78
- `task-start` records the base revision, target branch, task branch, and worktree
79
- in the repository manifest. `commit-push` is valid only inside that task's
80
- registered worktree and may stage only changes owned by that task. If unknown
81
- changes appear, stop and report them. Never restore, reset, stash, clean, or
82
- otherwise modify another task's or the user's changes.
95
+ `task-start` records the base revision, target branch, task branch, worktree,
96
+ owned paths, prerequisite task SHAs, and writer lease in the repository manifest.
97
+ Pass one `--owned-path` per owned path and one `--depends-on TASK_ID=SHA` per
98
+ prerequisite. The writer defaults to `CODEX_THREAD_ID`; pass `--writer` only when
99
+ an explicit stable identity is needed. Use `task-handoff` for an intentional
100
+ lease transfer; its generation check prevents a stale writer from reclaiming the
101
+ task. `commit-push` is valid only for the active writer inside the registered
102
+ worktree and may stage only owned paths. If unknown changes appear, stop and
103
+ report them. Never restore, reset, stash, clean, or otherwise modify another
104
+ task's or the user's changes.
105
+
106
+ After a reviewer returns, the main agent records the verdict and exact 64-character
107
+ diff fingerprint with `task-review`. Any content change invalidates that review.
108
+ `commit-push` and `task-integrate` require a current approval for the current
109
+ fingerprint and verify prerequisite SHAs. If integration enters a rebase conflict,
110
+ resolve it in the registered worktree, continue or abort the rebase as instructed,
111
+ then run `task-resume`; do not bypass the conflicted manifest state.
112
+
113
+ Treat `commit-push` plus `task-integrate` as one push stage. Run the fast gate
114
+ only in `commit-push`; integration fetches/rebases, safely pushes the target, and
115
+ cleans the task without repeating the gate. Successful target push ends the
116
+ coding task. Do not wait for or inspect Jenkins/build/deploy results afterward.
117
+ The task commit runs project commit hooks once. The internal backup task-branch
118
+ push skips the pre-push hook; the final target-branch push runs it once.
119
+ Integration creates no second evidence commit.
83
120
 
84
121
  After a successful integration, remove the clean worktree and merged local task
85
122
  branch. Delete the merged remote task branch by default. Use `task-finish` to
@@ -108,25 +145,27 @@ explicitly recovered.
108
145
 
109
146
  ## Development closure
110
147
 
111
- 1. Start the write task with `task-start` and enter its registered worktree.
112
- 2. Locate the real entry point, call chain, existing owner module, tests, and
113
- reusable helpers.
114
- 3. Update the active task with the smallest useful design note.
115
- 4. Create DD/ADR only for cross-module, API, DB, deployment/CI, security, key UI
148
+ 1. The main agent analyzes and decomposes the request into bounded units with
149
+ explicit dependencies, acceptance criteria, and owned paths.
150
+ 2. Run justified `explorer`, `docs_researcher`, and `browser_debugger` discovery
151
+ in parallel, then let the main agent merge their evidence into one design.
152
+ 3. Create DD/ADR only for cross-module, API, DB, deployment/CI, security, key UI
116
153
  flow, or lasting structural decisions.
117
- 5. Implement only necessary changes.
118
- 6. Run the resolved gate.
119
- 7. Record `DEV-CLOSED`, commit, push, integrate, and clean the task worktree.
120
-
121
- ## Verified closure
122
-
123
- High-risk or explicitly verified work uses the strongest path:
124
-
125
- 1. Run the real full local gate.
126
- 2. Commit and push.
127
- 3. Verify enabled CI/Jenkins and target-environment surfaces.
128
- 4. Record `PASS`, `FAIL`, or `PARTIAL` only from executed evidence.
129
- 5. Integrate successful work and clean its temporary worktree and branches.
154
+ 4. Start one registered task worktree per independent write unit and assign one
155
+ fixer to it. Parallelize only dependency-free units with non-overlapping paths;
156
+ deliver implementation → review → gate/integration in dependency waves, and
157
+ start the next wave only after its prerequisites are integrated.
158
+ 5. Review each stable diff with a read-only reviewer. Route blocking findings to
159
+ the owning fixer and re-review after any change. The main agent records the
160
+ current verdict with `task-review`, then hands the writer lease back before Git
161
+ closure when required.
162
+ 6. After all agents have returned, the main agent runs `commit-push` for each
163
+ write task; it executes the changed-scope fast gate once, records
164
+ `DEV-CLOSED`, commits, and pushes the task branch.
165
+ 7. The main agent runs `task-integrate` in dependency order to push the target
166
+ branch and clean every task worktree and merged task branch.
167
+ 8. Stop. Jenkins owns later build/deploy work and the project owner owns actual
168
+ acceptance. Ignore later external failures unless the user opens a diagnostic task.
130
169
 
131
170
  ## Structure policy
132
171
 
@@ -147,7 +186,7 @@ python3 docs/tools/autopipeline/ap.py baseline init --write --update-config
147
186
 
148
187
  Role templates provide behavior and permission boundaries, while the active
149
188
  client supplies the available model unless a project keeps an explicit override.
150
- `classify` recommends only roles justified by the effective profile:
189
+ `classify` returns both justified roles and a structured `agent_plan`:
151
190
 
152
191
  - `explorer`: read-only repository discovery and root-cause tracing.
153
192
  - `docs_researcher`: current official API/version research.
@@ -155,8 +194,28 @@ client supplies the available model unless a project keeps an explicit override.
155
194
  - `fixer`: bounded implementation after scope is clear.
156
195
  - `reviewer`: correctness, security, regression, and evidence review.
157
196
 
158
- The main agent owns framing, architecture decisions, integration, verification,
159
- closure records, and Git state.
197
+ For standard and high-risk write tasks, use the following fan-out/fan-in contract:
198
+
199
+ 1. The main agent owns decomposition and supplies every subagent with `task_id`,
200
+ role, scope, dependencies, acceptance criteria, and expected output.
201
+ 2. Discovery roles are read-only and may run in parallel. Browser work is limited
202
+ to requested reproduction/evidence; it does not replace owner acceptance.
203
+ 3. Each fixer receives a task branch, absolute worktree path, and owned paths.
204
+ It may edit only that worktree and must not commit, push, integrate, clean, or
205
+ run the project gate.
206
+ 4. Each reviewer receives a stable diff and binds approved or changes-requested
207
+ to its fingerprint. Changes go back to the same fixer and invalidate approval.
208
+ 5. Every subagent returns exactly one JSON object conforming to
209
+ `data/contracts/orchestration-v1.schema.json#/$defs/agentResult`, with integer
210
+ `contract_version: 1`. It includes node/task/role, base SHA, dependencies,
211
+ owned and changed paths, diff fingerprint, evidence, findings, verdict, risks,
212
+ and next owner. Read-only roles return no changed paths.
213
+ 6. The main agent alone owns architecture decisions, the single fast gate per
214
+ write task, closure records, commits, integration, push, and branch cleanup.
215
+
216
+ Micro tasks stay main-agent-only unless they contain genuinely independent work
217
+ whose benefit exceeds delegation overhead. If subagents are unavailable, the
218
+ main agent executes the same stages sequentially without weakening isolation.
160
219
 
161
220
  ## Tool routing
162
221
 
@@ -164,11 +223,11 @@ closure records, and Git state.
164
223
  - Current library/API behavior: official documentation MCP or matching skill.
165
224
  - UI: in-app browser for local pages, Chrome for existing logged-in state,
166
225
  Playwright for deterministic automation, Computer Use for unsupported native UI.
167
- - PR/issue/CI state: GitHub connector; local Git for local changes and pushes.
226
+ - PR/issue state: GitHub connector; local Git for local changes and pushes.
168
227
  - Design, security, analytics, and document artifacts: use the matching installed
169
228
  skill or connector before manual recreation.
170
- - Secrets: use configured environment references or secure platform flows; do
171
- not invent values.
229
+ - Credentials: use the direct values configured under `access.*` in
230
+ `docs/ENGINEERING.md`; do not invent or echo values unnecessarily.
172
231
 
173
232
  ## Optional documents and operations
174
233
 
@@ -177,11 +236,14 @@ python3 docs/tools/autopipeline/ap.py scaffold all --write
177
236
  python3 docs/tools/autopipeline/ap.py docs-ledger-check
178
237
  python3 docs/tools/autopipeline/ap.py docs-ledger-archive --plan
179
238
  python3 docs/tools/autopipeline/ap.py gate-profile
180
- python3 docs/tools/autopipeline/ap.py task-start <TASK_ID>
239
+ python3 docs/tools/autopipeline/ap.py task-start <TASK_ID> --owned-path <PATH> [--depends-on <TASK_ID=SHA>] [--writer <WRITER>]
181
240
  python3 docs/tools/autopipeline/ap.py task-status <TASK_ID>
182
241
  python3 docs/tools/autopipeline/ap.py task-submodule-sync <TASK_ID>
183
- python3 docs/tools/autopipeline/ap.py commit-push <TASK_ID> --msg "<TASK_ID>: <summary>"
242
+ python3 docs/tools/autopipeline/ap.py task-review <TASK_ID> --verdict <VERDICT> --diff-fingerprint <SHA256> [--reviewer <REVIEWER>]
243
+ python3 docs/tools/autopipeline/ap.py task-handoff <TASK_ID> --from <WRITER> --to <WRITER> [--generation <N>]
244
+ python3 docs/tools/autopipeline/ap.py commit-push <TASK_ID> --msg "<TASK_ID>: <summary>" [--writer <WRITER>]
184
245
  python3 docs/tools/autopipeline/ap.py task-integrate <TASK_ID>
246
+ python3 docs/tools/autopipeline/ap.py task-resume <TASK_ID>
185
247
  python3 docs/tools/autopipeline/ap.py task-finish <TASK_ID>
186
248
  python3 docs/tools/autopipeline/ap.py task-prune
187
249
  ```