@tacuchi/agent-workflow-cli 15.2.0 → 16.0.0
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.
- package/package.json +1 -1
- package/skills/w/README.md +14 -14
- package/skills/w/SKILL.md +94 -82
- package/skills/w/artifacts/artifacts-core/TASKS.md +1 -1
- package/skills/w/artifacts/artifacts-research/CONCLUSIONS.md +1 -1
- package/skills/w/commands/README.md +22 -22
- package/skills/w/commands/export-diagrams.md +9 -9
- package/skills/w/commands/export-manuals.md +9 -9
- package/skills/w/commands/export-reports.md +9 -9
- package/skills/w/commands/export-scripts.md +9 -9
- package/skills/w/commands/fix-git.md +12 -12
- package/skills/w/commands/plan-exec.md +19 -19
- package/skills/w/commands/plan-new.md +18 -18
- package/skills/w/commands/plan-refine.md +22 -22
- package/skills/w/commands/quick.md +16 -16
- package/skills/w/commands/spec-new.md +35 -34
- package/skills/w/commands/spec-refine.md +16 -16
- package/skills/w/commands/status.md +18 -16
- package/skills/w/commands/workspace-init.md +14 -14
- package/skills/w/exports/README.md +5 -5
- package/skills/w/exports/export-diagrams/SKILL.md +58 -58
- package/skills/w/exports/export-manuals/SKILL.md +61 -61
- package/skills/w/exports/export-reports/SKILL.md +51 -51
- package/skills/w/exports/export-scripts/SKILL.md +60 -60
- package/skills/w/harness/SKILL.md +48 -47
- package/skills/w/loops/CHASSIS.md +101 -98
- package/skills/w/loops/CODE-POLICIES.md +21 -21
- package/skills/w/loops/README.md +30 -29
- package/skills/w/loops/plan-exec-loop/SKILL.md +77 -77
- package/skills/w/loops/plan-new-loop/SKILL.md +80 -80
- package/skills/w/loops/plan-refine-loop/SKILL.md +62 -62
- package/skills/w/loops/quick-loop/SKILL.md +79 -79
- package/skills/w/loops/spec-refine-loop/SKILL.md +93 -94
- package/skills/w/roles/README.md +2 -2
- package/skills/w/roles/diagrams/SKILL.md +50 -47
- package/skills/w/roles/git/SKILL.md +58 -58
- package/skills/w/roles/research/SKILL.md +65 -62
- package/skills/w/roles/sql/SKILL.md +59 -55
- package/skills/w/roles/ui-spec/SKILL.md +60 -74
|
@@ -1,127 +1,127 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: export-manuals
|
|
3
|
-
description: "
|
|
3
|
+
description: "Operations / onboarding manuals (operator/support audience). Synthesizes the workspace's technical manuals into `docs/manuals/` consolidating N sessions (`exec`/`quick`) + `docs/`. Reads each session's `DECISION` and the plan-doc (`Solution`, `Final behavior`, `Validations`) + the touched code in the sources (how what was built operates/works). Two modes: `complement` (default, overwrites `INDEX.md` pointing at the detected manuals) and `regenerate` (produces a `NNN-export-manuals-YYYY-MM-DD/` dossier with 1 manual per topic). Audience: operators / support / onboarding. Read-only/report: it never commits nor mutates sessions. The prose follows the ambient writing conventions (the host auto-applies an installed writing skill when present). Use for 'operations manual', 'how what we shipped works', 'technical onboarding pack', 'manuals index'. User-invoked via `/w:export-manuals`."
|
|
4
4
|
---
|
|
5
5
|
|
|
6
|
-
# export-manuals —
|
|
6
|
+
# export-manuals — technical manuals from sessions + `docs/`
|
|
7
7
|
|
|
8
|
-
|
|
8
|
+
Generates or refreshes **operations / how-it-works / onboarding** manuals in `docs/manuals/`, consolidating what N sessions delivered + the `docs/` corpus. **Read-only / report** — it never commits, never mutates sessions or code.
|
|
9
9
|
|
|
10
|
-
>
|
|
10
|
+
> `export-*` family (the only artifact→`docs/` path). Design: `docs/referencias/workflow-exports/export-manuals.md`.
|
|
11
11
|
|
|
12
12
|
## Category
|
|
13
13
|
|
|
14
|
-
`docs/manuals` —
|
|
14
|
+
`docs/manuals` — the **only** `docs/` folder this export writes.
|
|
15
15
|
|
|
16
|
-
## Writing (
|
|
16
|
+
## Writing (ambient convention, not a role)
|
|
17
17
|
|
|
18
|
-
|
|
18
|
+
The manual's prose follows the **ambient** writing conventions: the host auto-applies an installed writing skill (when present) by its `description` — short sentences, lists over prose, no filler, technical lexicon for the operator/support audience. This export does **not** compose or bind a `writing` role; it is **indifferent** to which writing skill exists. A useful family lives in the `dev-conventions` marketplace plugin, but the export does **not depend** on it. Manuals are user-facing deliverables → write them in the user's language.
|
|
19
19
|
|
|
20
20
|
## When to use
|
|
21
21
|
|
|
22
|
-
- "
|
|
23
|
-
- "
|
|
24
|
-
-
|
|
25
|
-
-
|
|
22
|
+
- "Operations manual", "how what we delivered works", "step-by-step guide".
|
|
23
|
+
- "Manuals index" / refresh the `INDEX.md` after new sessions.
|
|
24
|
+
- **Technical onboarding** pack for new team members.
|
|
25
|
+
- Documentation-coverage audit.
|
|
26
26
|
|
|
27
27
|
## What it does
|
|
28
28
|
|
|
29
|
-
1.
|
|
30
|
-
2.
|
|
31
|
-
3.
|
|
32
|
-
4.
|
|
33
|
-
5.
|
|
34
|
-
6.
|
|
29
|
+
1. Reads the session corpus (`exec`/`quick`): per session, `DECISION` + the plan-doc (`Solution`, `Final behavior`, `Validations`).
|
|
30
|
+
2. Inspects the touched code in the sources (how what was built operates/works) — read-only.
|
|
31
|
+
3. Detects topics (declared in `SESSION` — its `## Objective` —, or inferred by operational keywords).
|
|
32
|
+
4. Resolves the mode (`complement` or `regenerate`).
|
|
33
|
+
5. Synthesizes the content applying the ambient writing conventions (host).
|
|
34
|
+
6. Writes: `complement` → overwrites `docs/manuals/INDEX.md`; `regenerate` → a `docs/manuals/NNN-export-manuals-YYYY-MM-DD/` dossier with 1 manual per topic.
|
|
35
35
|
|
|
36
36
|
## What it does NOT do
|
|
37
37
|
|
|
38
|
-
-
|
|
39
|
-
-
|
|
40
|
-
-
|
|
41
|
-
-
|
|
42
|
-
-
|
|
43
|
-
-
|
|
38
|
+
- Run commits, merges, push, SQL or send emails.
|
|
39
|
+
- Mutate sessions, the plan-doc, or the sources' code (read-only).
|
|
40
|
+
- Write any `docs/` folder other than `docs/manuals/` (invariant: one category).
|
|
41
|
+
- Overwrite a previous `regenerate` dossier (always next-number).
|
|
42
|
+
- Invent manuals: with no detectable topic → in `regenerate` it aborts with a clear message; in `complement` it produces an empty `INDEX.md` with an inline note.
|
|
43
|
+
- Visually render diagrams (visual architecture belongs to `export-diagrams`; embedded Mermaid only when it adds value).
|
|
44
44
|
|
|
45
45
|
## Read-only sandbox
|
|
46
46
|
|
|
47
|
-
|
|
47
|
+
In plan mode it **describes**, never writes: the resolved mode, the detected topics (with origin sessions), the manuals already present in `docs/manuals/`, and — per mode — the `INDEX.md` structure it would overwrite or the count of manuals the dossier would generate. It does **not** run `Write` or effectful `aw next-number`.
|
|
48
48
|
|
|
49
49
|
## Inputs
|
|
50
50
|
|
|
51
|
-
|
|
51
|
+
**`agent-workflow` CLI (alias `aw`)** — never read hardcoded paths:
|
|
52
52
|
|
|
53
|
-
- `aw sessions` / `aw release-data [--since sessionNNN] [--source <alias>]` —
|
|
54
|
-
- `aw session-artifacts --code <NNN> --dump objetivo,decisiones` —
|
|
55
|
-
- `aw next-number docs/manuals` —
|
|
53
|
+
- `aw sessions` / `aw release-data [--since sessionNNN] [--source <alias>]` — enumerates the corpus.
|
|
54
|
+
- `aw session-artifacts --code <NNN> --dump objetivo,decisiones` — returns `{path, content, size}` per artifact (`SESSION` with its `## Objective`, `DECISION`); the plan-doc is read by its path.
|
|
55
|
+
- `aw next-number docs/manuals` — deterministic numbering (`regenerate` mode only).
|
|
56
56
|
|
|
57
57
|
**Filesystem**:
|
|
58
58
|
|
|
59
|
-
- `docs/manuals/*.md` —
|
|
60
|
-
- `docs/manuals/INDEX.md` — re-generable (
|
|
61
|
-
-
|
|
59
|
+
- `docs/manuals/*.md` — manuals already present (to complement).
|
|
60
|
+
- `docs/manuals/INDEX.md` — re-generable (overwritable) in `complement` mode.
|
|
61
|
+
- The declared sources' code — read to describe behavior.
|
|
62
62
|
|
|
63
|
-
**Args** (
|
|
63
|
+
**Args** (no lifecycle *structured-choice*; harness capability — see [`../../harness/SKILL.md`](../../harness/SKILL.md)):
|
|
64
64
|
|
|
65
65
|
```
|
|
66
66
|
/w:export-manuals [--sessions NNN[,NNN]] [--since sessionNNN] [--source <alias>]
|
|
67
67
|
[--mode complement|regenerate] [--topics slug1,slug2] [--dry-run]
|
|
68
68
|
```
|
|
69
69
|
|
|
70
|
-
| Flag |
|
|
70
|
+
| Flag | Behavior |
|
|
71
71
|
|---|---|
|
|
72
|
-
| `--sessions NNN[,NNN]` |
|
|
73
|
-
| `--since sessionNNN` |
|
|
74
|
-
| `--source <alias>` |
|
|
72
|
+
| `--sessions NNN[,NNN]` | Discrete filter by code (takes precedence over `--since`) |
|
|
73
|
+
| `--since sessionNNN` | Only sessions after NNN (exclusive: NNN itself is out; use `--sessions` to include it) |
|
|
74
|
+
| `--source <alias>` | Limits to one source (multi-source workspace) |
|
|
75
75
|
| `--mode complement\|regenerate` | Default `complement` |
|
|
76
|
-
| `--topics slug1,slug2` |
|
|
77
|
-
| `--dry-run` |
|
|
76
|
+
| `--topics slug1,slug2` | Limits to the declared topics |
|
|
77
|
+
| `--dry-run` | Propositional report, no files written |
|
|
78
78
|
|
|
79
|
-
|
|
79
|
+
No args: `--mode complement` over the whole corpus.
|
|
80
80
|
|
|
81
|
-
###
|
|
81
|
+
### `--mode` resolution
|
|
82
82
|
|
|
83
|
-
|
|
|
83
|
+
| Mode | Output | When to use |
|
|
84
84
|
|---|---|---|
|
|
85
|
-
| `complement` (default) | `docs/manuals/INDEX.md` (
|
|
86
|
-
| `regenerate` | `docs/manuals/NNN-export-manuals-YYYY-MM-DD/` (next-number) |
|
|
85
|
+
| `complement` (default) | `docs/manuals/INDEX.md` (overwrites) | Refresh the index after new sessions/manuals |
|
|
86
|
+
| `regenerate` | `docs/manuals/NNN-export-manuals-YYYY-MM-DD/` (next-number) | Consolidated manual pack (e.g. onboarding) |
|
|
87
87
|
|
|
88
88
|
## Flow
|
|
89
89
|
|
|
90
|
-
###
|
|
90
|
+
### Step 1 — Resolve context and corpus
|
|
91
91
|
|
|
92
|
-
`aw sessions` / `release-data`
|
|
92
|
+
`aw sessions` / `release-data` applying `--sessions`/`--since`/`--source`. The CLI handles destination-folder resolution.
|
|
93
93
|
|
|
94
|
-
###
|
|
94
|
+
### Step 2 — Inspect the present manuals
|
|
95
95
|
|
|
96
|
-
|
|
96
|
+
List `docs/manuals/*.md` (excluding `INDEX.md` and `NNN-export-manuals-*/` subdirectories). Per manual: slug (from the filename), title (first `#`), brief summary (first paragraph), path.
|
|
97
97
|
|
|
98
|
-
###
|
|
98
|
+
### Step 3 — Detect topics
|
|
99
99
|
|
|
100
|
-
|
|
100
|
+
For every filtered corpus session (`aw session-artifacts --code <NNN> --dump objetivo,decisiones`): take the dump's `DECISION` + the plan-doc (`Solution`/`Final behavior`/`Validations`) + the touched code. **Primary** topic: the topic in `SESSION` (its `## Objective`). **Secondary**: inference by operational keywords ("configure", "install", "step by step", "how to …" — in the user's language). Filter by `--topics` when present. List (slug, confidence, origin sessions).
|
|
101
101
|
|
|
102
|
-
###
|
|
102
|
+
### Step 4 — Synthesize (prose: ambient conventions)
|
|
103
103
|
|
|
104
|
-
**
|
|
104
|
+
**`complement` mode** — one `INDEX.md`: header + manual count + table (Topic · Slug · Manual present/`[pending]` · Origin sessions) + "Next steps" when there are pending topics.
|
|
105
105
|
|
|
106
|
-
**
|
|
106
|
+
**`regenerate` mode** — 1 `.md` per topic in the dossier, each with: Purpose · Prerequisites · Numbered steps (how to operate) · Final behavior (from the plan-doc) · Post-use validation · Relevant decisions (`DECISION`) · Troubleshooting · References. Every manual must let the operator complete the task **without** calling the development team. Plus a dossier `README.md` with the index. The prose follows the ambient writing conventions (host).
|
|
107
107
|
|
|
108
|
-
###
|
|
108
|
+
### Step 5 — Write or report
|
|
109
109
|
|
|
110
|
-
|
|
110
|
+
With `--dry-run`: print the report; write nothing. Otherwise: `complement` → `Write` over `docs/manuals/INDEX.md`; `regenerate` → `aw next-number docs/manuals` + create the dossier. **NEVER commit**. Summary to the user: mode + written paths + counts; if there are detectable topics without a manual, suggest covering them.
|
|
111
111
|
|
|
112
112
|
## Output location
|
|
113
113
|
|
|
114
|
-
- `complement`: `docs/manuals/INDEX.md` (
|
|
115
|
-
- `regenerate`: `docs/manuals/NNN-export-manuals-YYYY-MM-DD/`
|
|
114
|
+
- `complement`: `docs/manuals/INDEX.md` (overwrites).
|
|
115
|
+
- `regenerate`: `docs/manuals/NNN-export-manuals-YYYY-MM-DD/` with `README.md` + 1 `.md` per topic.
|
|
116
116
|
|
|
117
117
|
## Re-run
|
|
118
118
|
|
|
119
|
-
- `complement`:
|
|
120
|
-
- `regenerate`:
|
|
119
|
+
- `complement`: idempotent — two invocations over the same corpus produce the same `INDEX.md`.
|
|
120
|
+
- `regenerate`: each invocation takes the next `NNN`; it never overwrites previous dossiers.
|
|
121
121
|
|
|
122
122
|
## Resources
|
|
123
123
|
|
|
124
|
-
- Design: `docs/referencias/workflow-exports/export-manuals.md` ·
|
|
125
|
-
-
|
|
126
|
-
-
|
|
124
|
+
- Design: `docs/referencias/workflow-exports/export-manuals.md` · family: [`../README.md`](../README.md).
|
|
125
|
+
- Writing: **ambient** convention (not a role) — the host auto-applies an installed writing skill when present.
|
|
126
|
+
- Source artifacts: `DECISION` + plan-doc (see `docs/referencias/workflow-artifacts/artifacts-exec/` and `docs/specs`/`docs/plans`).
|
|
127
127
|
- Siblings: [`../export-scripts/SKILL.md`](../export-scripts/SKILL.md) · [`../export-diagrams/SKILL.md`](../export-diagrams/SKILL.md) · [`../export-reports/SKILL.md`](../export-reports/SKILL.md).
|
|
@@ -1,101 +1,101 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: export-reports
|
|
3
|
-
description: "
|
|
3
|
+
description: "Executive/functional report (management/committee audience) consolidating N workspace sessions under `docs/reports/NNN-<slug>-YYYY-MM-DD.md`. Reads the corpus: the spec (`docs/specs`), `CONCLUSIONS` (research), `DECISION`, the plan-doc state + the rest of `docs/` for context. Synthesizes: what was done, key decisions, results/conclusions, pending/roadmap — with cross-session recommendation dedup. Audience adjustable via `--audience` (gerencia ≈ short; tecnica ≈ detailed). Read-only/report: it never commits nor mutates sessions. The prose follows the ambient writing conventions (the host auto-applies an installed writing skill when present). Use for 'executive report', 'what got done this quarter for management', 'brief with consolidated recommendations'. User-invoked via `/w:export-reports`."
|
|
4
4
|
---
|
|
5
5
|
|
|
6
|
-
# export-reports —
|
|
6
|
+
# export-reports — executive/functional report from the session corpus + `docs/`
|
|
7
7
|
|
|
8
|
-
|
|
8
|
+
Generates a single `.md` consolidating N workspace sessions into an **executive/functional** report: what was done, key decisions, results/conclusions and pending/roadmap. **Read-only / report** — it never commits, never mutates sessions or the corpus.
|
|
9
9
|
|
|
10
|
-
>
|
|
10
|
+
> `export-*` family (the only artifact→`docs/` path). It **merges** two legacy exports into one `docs/reports` output: the executive report and the cross-session recommendation dedup. Design: `docs/referencias/workflow-exports/export-reports.md`.
|
|
11
11
|
|
|
12
12
|
## Category
|
|
13
13
|
|
|
14
|
-
`docs/reports` —
|
|
14
|
+
`docs/reports` — the **only** `docs/` folder this export writes.
|
|
15
15
|
|
|
16
|
-
## Writing (
|
|
16
|
+
## Writing (ambient convention, not a role)
|
|
17
17
|
|
|
18
|
-
|
|
18
|
+
The report's prose follows the **ambient** writing conventions: the host auto-applies an installed writing skill (when present) by its `description` — technical→executive translation, per-audience length cap, short sentences, lists over prose, no filler. This export does **not** compose or bind a `writing` role. Reports are user-facing deliverables → write them in the user's language.
|
|
19
19
|
|
|
20
20
|
## When to use
|
|
21
21
|
|
|
22
|
-
- "
|
|
23
|
-
-
|
|
24
|
-
- Re-
|
|
22
|
+
- "Executive report", "functional document", "what got done this quarter for management".
|
|
23
|
+
- A brief with the **consolidated** (deduplicated) recommendations of the last N sessions.
|
|
24
|
+
- Re-generate after a new period (month / quarter); before a follow-up committee.
|
|
25
25
|
|
|
26
26
|
## What it does
|
|
27
27
|
|
|
28
|
-
1.
|
|
29
|
-
2.
|
|
30
|
-
3.
|
|
31
|
-
4.
|
|
32
|
-
5. **
|
|
33
|
-
6.
|
|
28
|
+
1. Reads the filtered session corpus: the spec (`docs/specs`), `CONCLUSIONS` (research), `DECISION`, the plan-doc state.
|
|
29
|
+
2. Reads the rest of `docs/` (specs, plans, previous reports) for context.
|
|
30
|
+
3. Resolves the audience/length (`--audience`).
|
|
31
|
+
4. Synthesizes: Executive summary · What was done (grouped by business capability, not by session) · Key decisions · Results/conclusions · Pending/Roadmap.
|
|
32
|
+
5. **Deduplicates** the recommendations (R-items) cross-session by slug, annotating the origins.
|
|
33
|
+
6. Writes `docs/reports/NNN-<slug>-YYYY-MM-DD.md`.
|
|
34
34
|
|
|
35
35
|
## What it does NOT do
|
|
36
36
|
|
|
37
|
-
-
|
|
38
|
-
-
|
|
39
|
-
-
|
|
40
|
-
-
|
|
41
|
-
-
|
|
42
|
-
-
|
|
37
|
+
- Run commits, merges, push, SQL, emails or PR creation.
|
|
38
|
+
- Mutate sessions, the corpus or the plan-doc (read-only).
|
|
39
|
+
- Write any `docs/` folder other than `docs/reports/` (invariant: one category).
|
|
40
|
+
- Invent achievements, metrics or recommendations: conditional sections (e.g. "Improvement opportunities"/Roadmap) appear **only** when the corpus has detectable open items.
|
|
41
|
+
- Generate advanced technical diagrams (extensive C4/erDiagram) — those live in `export-diagrams`; here, at most a simple executive-synthesis `flowchart LR`.
|
|
42
|
+
- Overwrite previous reports (always next-number).
|
|
43
43
|
|
|
44
44
|
## Read-only sandbox
|
|
45
45
|
|
|
46
|
-
|
|
46
|
+
In plan mode it **describes**, never writes: the resolved audience/length, the corpus sessions that would enter after the filters, the sections that would appear, the R-items that would consolidate (and detected conflicts), and the estimated length. It does **not** run `Write` or effectful `aw next-number`.
|
|
47
47
|
|
|
48
48
|
## Inputs
|
|
49
49
|
|
|
50
|
-
|
|
50
|
+
**`agent-workflow` CLI (alias `aw`)** — never read hardcoded paths:
|
|
51
51
|
|
|
52
|
-
- `aw sessions` / `aw release-data [--since sessionNNN] [--source <alias>]` —
|
|
53
|
-
- `aw session-artifacts --code <NNN> --dump objetivo,conclusiones,decisiones` —
|
|
54
|
-
- `aw next-number docs/reports` —
|
|
52
|
+
- `aw sessions` / `aw release-data [--since sessionNNN] [--source <alias>]` — enumerates + filters the corpus.
|
|
53
|
+
- `aw session-artifacts --code <NNN> --dump objetivo,conclusiones,decisiones` — returns `{path, content, size}` for `SESSION` (referenced spec), `CONCLUSIONS` and `DECISION`; the plan-doc state is read by its path.
|
|
54
|
+
- `aw next-number docs/reports` — deterministic numbering (the CLI handles destination-folder resolution).
|
|
55
55
|
|
|
56
56
|
**Filesystem**:
|
|
57
57
|
|
|
58
|
-
- `docs/specs`, `docs/plans`, `docs/reports/*` —
|
|
58
|
+
- `docs/specs`, `docs/plans`, `docs/reports/*` — context + collision avoidance.
|
|
59
59
|
|
|
60
|
-
**Args** (
|
|
60
|
+
**Args** (no lifecycle *structured-choice*; harness capability — see [`../../harness/SKILL.md`](../../harness/SKILL.md)):
|
|
61
61
|
|
|
62
62
|
```
|
|
63
63
|
/w:export-reports [--sessions NNN[,NNN]] [--since sessionNNN] [--source <alias>]
|
|
64
64
|
[--audience gerencia|tecnica] [--slug <kebab>] [--dry-run]
|
|
65
65
|
```
|
|
66
66
|
|
|
67
|
-
| Flag |
|
|
67
|
+
| Flag | Behavior |
|
|
68
68
|
|---|---|
|
|
69
|
-
| `--sessions NNN[,NNN]` |
|
|
70
|
-
| `--since sessionNNN` |
|
|
71
|
-
| `--source <alias>` |
|
|
72
|
-
| `--audience gerencia\|tecnica` |
|
|
73
|
-
| `--slug <kebab>` |
|
|
74
|
-
| `--dry-run` |
|
|
69
|
+
| `--sessions NNN[,NNN]` | Discrete filter by code (takes precedence over `--since`) |
|
|
70
|
+
| `--since sessionNNN` | Only sessions after NNN (exclusive: NNN itself is out; use `--sessions` to include it) |
|
|
71
|
+
| `--source <alias>` | Limits to one source (multi-source workspace) |
|
|
72
|
+
| `--audience gerencia\|tecnica` | Modulates length/lexicon: `gerencia` ≈ short/executive; `tecnica` ≈ detailed |
|
|
73
|
+
| `--slug <kebab>` | Filename slug override (default: `export-reports`) |
|
|
74
|
+
| `--dry-run` | Propositional report, no writing |
|
|
75
75
|
|
|
76
|
-
|
|
76
|
+
No args: the whole corpus, executive audience by default.
|
|
77
77
|
|
|
78
78
|
## Flow
|
|
79
79
|
|
|
80
|
-
###
|
|
80
|
+
### Step 1 — Resolve context and filter the corpus
|
|
81
81
|
|
|
82
|
-
`aw sessions` / `release-data`
|
|
82
|
+
`aw sessions` / `release-data` applying `--sessions`/`--since`/`--source`. If the resulting set is empty → **abort** with an explicit message (no sessions in the declared range). The CLI handles destination-folder resolution.
|
|
83
83
|
|
|
84
|
-
###
|
|
84
|
+
### Step 2 — Collect per-session inputs
|
|
85
85
|
|
|
86
|
-
|
|
86
|
+
Per filtered session (`aw session-artifacts --code <NNN> --dump objetivo,conclusiones,decisiones`): the referenced spec (what was posed), `CONCLUSIONS` (technical close / R-items), `DECISION` (what was decided), the plan-doc state (what shipped / what remains). Also collect the impacted components (touched sources) for the synthesis table.
|
|
87
87
|
|
|
88
|
-
###
|
|
88
|
+
### Step 3 — Recommendation dedup (cross-session)
|
|
89
89
|
|
|
90
|
-
|
|
90
|
+
Extract the R-items from `CONCLUSIONS`/`DECISION` (pending, deferred, "next steps"). Group by slug; merge duplicates annotating `origins[]`; if two same-slug R-items contradict each other, mark them as a conflict for explicit resolution. Do **not** dedup the C-items (they are analysis-specific: preserved with traceability).
|
|
91
91
|
|
|
92
|
-
###
|
|
92
|
+
### Step 4 — Synthesize (prose: ambient conventions)
|
|
93
93
|
|
|
94
|
-
Render
|
|
94
|
+
Render applying the ambient writing conventions (host): Executive summary · What was done (grouped by business capability, **not** by session) · Impacted components (table) · Key decisions · Results/conclusions · Pending/Roadmap (only with R-items). Technical→executive translation and length cap per `--audience`. Optional: a simple synthesis `flowchart LR` (with a `mermaid.ink` link); the detailed technical diagram belongs to `export-diagrams`.
|
|
95
95
|
|
|
96
|
-
###
|
|
96
|
+
### Step 5 — Write or report
|
|
97
97
|
|
|
98
|
-
`aw next-number docs/reports` → `docs/reports/NNN-<slug>-YYYY-MM-DD.md`.
|
|
98
|
+
`aw next-number docs/reports` → `docs/reports/NNN-<slug>-YYYY-MM-DD.md`. With `--dry-run`: print; write nothing. **NEVER commit**. Summary to the user: path, audience/length, covered sessions (count + range), consolidated R-items, and a note if a conditional section was omitted.
|
|
99
99
|
|
|
100
100
|
## Output location
|
|
101
101
|
|
|
@@ -103,11 +103,11 @@ Render aplicando las convenciones de redacción ambientes (host): Resumen ejecut
|
|
|
103
103
|
|
|
104
104
|
## Re-run
|
|
105
105
|
|
|
106
|
-
|
|
106
|
+
Functionally idempotent: each invocation takes the next `NNN`; it never overwrites previous reports. To regenerate the latest: delete the file and re-invoke.
|
|
107
107
|
|
|
108
108
|
## Resources
|
|
109
109
|
|
|
110
|
-
- Design: `docs/referencias/workflow-exports/export-reports.md` ·
|
|
111
|
-
-
|
|
112
|
-
-
|
|
110
|
+
- Design: `docs/referencias/workflow-exports/export-reports.md` · family: [`../README.md`](../README.md).
|
|
111
|
+
- Writing: **ambient** convention (not a role) — the host auto-applies an installed writing skill when present.
|
|
112
|
+
- Inputs: spec (`docs/specs`), `CONCLUSIONS`/`DECISION` (see `docs/referencias/workflow-artifacts/`), plan-doc (`docs/plans`).
|
|
113
113
|
- Siblings: [`../export-scripts/SKILL.md`](../export-scripts/SKILL.md) · [`../export-manuals/SKILL.md`](../export-manuals/SKILL.md) · [`../export-diagrams/SKILL.md`](../export-diagrams/SKILL.md).
|