gspec 1.16.0 → 1.17.1
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.
- package/README.md +33 -6
- package/bin/emitters.js +104 -0
- package/bin/gspec.js +214 -33
- package/commands/gspec.analyze.md +9 -0
- package/commands/gspec.audit.md +84 -9
- package/commands/gspec.feature.md +10 -0
- package/commands/gspec.implement.md +19 -8
- package/commands/gspec.tasks.md +150 -0
- package/dist/antigravity/gspec-analyze/SKILL.md +9 -0
- package/dist/antigravity/gspec-audit/SKILL.md +85 -10
- package/dist/antigravity/gspec-feature/SKILL.md +10 -0
- package/dist/antigravity/gspec-implement/SKILL.md +19 -8
- package/dist/antigravity/gspec-tasks/SKILL.md +154 -0
- package/dist/claude/gspec-analyze/SKILL.md +9 -0
- package/dist/claude/gspec-audit/SKILL.md +85 -10
- package/dist/claude/gspec-feature/SKILL.md +10 -0
- package/dist/claude/gspec-implement/SKILL.md +19 -8
- package/dist/claude/gspec-tasks/SKILL.md +155 -0
- package/dist/codex/gspec-analyze/SKILL.md +9 -0
- package/dist/codex/gspec-audit/SKILL.md +85 -10
- package/dist/codex/gspec-feature/SKILL.md +10 -0
- package/dist/codex/gspec-implement/SKILL.md +19 -8
- package/dist/codex/gspec-tasks/SKILL.md +154 -0
- package/dist/cursor/gspec-analyze.mdc +9 -0
- package/dist/cursor/gspec-audit.mdc +85 -10
- package/dist/cursor/gspec-feature.mdc +10 -0
- package/dist/cursor/gspec-implement.mdc +19 -8
- package/dist/cursor/gspec-tasks.mdc +153 -0
- package/dist/opencode/gspec-analyze/SKILL.md +9 -0
- package/dist/opencode/gspec-audit/SKILL.md +85 -10
- package/dist/opencode/gspec-feature/SKILL.md +10 -0
- package/dist/opencode/gspec-implement/SKILL.md +19 -8
- package/dist/opencode/gspec-tasks/SKILL.md +154 -0
- package/package.json +1 -1
- package/templates/spec-sync.md +2 -1
|
@@ -191,6 +191,16 @@ When generating multiple features from a large request:
|
|
|
191
191
|
|
|
192
192
|
---
|
|
193
193
|
|
|
194
|
+
## After Writing the PRD
|
|
195
|
+
|
|
196
|
+
After saving each PRD, end your response with a brief next-step pointer:
|
|
197
|
+
|
|
198
|
+
> *For larger features, run `/gspec-tasks <feature-slug>` to produce an ordered task plan with explicit dependencies and parallel-execution markers before running `/gspec-implement`. Trivial features can skip straight to `/gspec-implement`.*
|
|
199
|
+
|
|
200
|
+
This is a one-line nudge, not a prompt — do not generate the tasks file from this skill, and do not block the user on it.
|
|
201
|
+
|
|
202
|
+
---
|
|
203
|
+
|
|
194
204
|
## Tone & Style
|
|
195
205
|
|
|
196
206
|
- Clear, neutral, product-led
|
|
@@ -26,6 +26,7 @@ Before writing any code, read all available gspec documents in this order:
|
|
|
26
26
|
1. `gspec/profile.md` — Understand what the product is and who it's for
|
|
27
27
|
2. `gspec/features/*.md` — Understand individual feature requirements and dependencies
|
|
28
28
|
> **Note:** Feature PRDs are designed to be portable and project-agnostic. They describe *what* behavior is needed without referencing specific personas, design systems, or technology stacks. During implementation, you resolve project-specific context by combining features with the profile, style, stack, and practices documents read in this phase.
|
|
29
|
+
3. `gspec/features/*.tasks.md` — For any feature in scope, also read its tasks file if one exists. Tasks files are produced by `gspec-tasks` and contain an ordered, dependency-aware breakdown of the PRD's capabilities into concrete implementation tasks with `[P]` parallel markers and explicit `deps:` lines. **When a tasks file exists, it is the authoritative build order for that feature.** When it doesn't exist, fall back to the PRD's checkbox capabilities directly.
|
|
29
30
|
4. `gspec/stack.md` — Understand the technology choices
|
|
30
31
|
5. `gspec/style.md` **or** `gspec/style.html` — Understand the visual design language. The style guide may be in either format; read whichever exists (or both, if both are present — the HTML file contains the renderable token definitions and visual examples, the Markdown file contains prose rationale)
|
|
31
32
|
6. `gspec/design/**` — If this folder exists, read every mockup in it. Supported formats include HTML pages, SVG files, and image files (PNG, JPG, WEBP). These are visual mockups (typically produced by external design tools like Figma, v0, Framer AI, etc.) that show layout, composition, and visual intent for specific screens or flows. **Treat them as authoritative visual guidance** — when building UI for a feature, look for relevant mockups in `gspec/design/` and match their layout, spacing, and hierarchy within the constraints of the style guide
|
|
@@ -46,10 +47,16 @@ This command is designed to be **run multiple times** as features are added or e
|
|
|
46
47
|
- **`- [ ]`** (unchecked) = capability not yet implemented — include in this run's scope
|
|
47
48
|
- **No checkbox prefix** = treat as not yet implemented (backwards compatible with older PRDs)
|
|
48
49
|
|
|
50
|
+
**When a feature has a tasks file** (`gspec/features/<feature>.tasks.md`), also assess task-level state:
|
|
51
|
+
|
|
52
|
+
- A task with `- [x]` is complete; skip unless user requests re-implementation
|
|
53
|
+
- A task with `- [ ]` is pending and goes into this run's scope
|
|
54
|
+
- A capability is considered fully delivered only when **every** task whose `covers:` references it is `- [x]`. A PRD capability checkbox should never be checked while one of its covering tasks is still unchecked, and vice versa — flag any such inconsistency to the user
|
|
55
|
+
|
|
49
56
|
For each feature PRD, build an implementation status summary:
|
|
50
57
|
|
|
51
|
-
> **Feature: User Authentication** — 4/7 capabilities implemented (all P0 done, 3 P1/P2 remaining)
|
|
52
|
-
> **Feature: Dashboard** — 0/5 capabilities implemented (new feature)
|
|
58
|
+
> **Feature: User Authentication** — 4/7 capabilities implemented (all P0 done, 3 P1/P2 remaining); tasks file shows 8/14 tasks done
|
|
59
|
+
> **Feature: Dashboard** — 0/5 capabilities implemented (new feature, no tasks file)
|
|
53
60
|
|
|
54
61
|
Present this summary to the user so they understand the starting point. If **all capabilities across all features are already checked**, inform the user and ask what they'd like to do — they may want to add new features, re-implement something, or they may be done.
|
|
55
62
|
|
|
@@ -57,14 +64,15 @@ Present this summary to the user so they understand the starting point. If **all
|
|
|
57
64
|
|
|
58
65
|
**Enter plan mode** and create a concrete, phased implementation plan.
|
|
59
66
|
|
|
60
|
-
1. **Survey the full scope** — Review all feature PRDs and identify every unchecked capability that is in scope for this run
|
|
61
|
-
2. **Organize into implementation phases** — Group related
|
|
67
|
+
1. **Survey the full scope** — Review all feature PRDs and identify every unchecked capability that is in scope for this run. For features that have a tasks file, the unchecked tasks (not just capabilities) are the actual unit of work.
|
|
68
|
+
2. **Organize into implementation phases** — Group related work into logical phases that can be built and verified independently. Each phase should:
|
|
62
69
|
- Have a clear name and objective (e.g., "Phase 1: Core Data Models & API", "Phase 2: Authentication Flow")
|
|
63
|
-
- List the specific capabilities (with feature PRD references) it will implement
|
|
70
|
+
- List the specific capabilities (with feature PRD references) it will implement, **and the specific tasks (by ID, e.g. T1, T2, T7) when a tasks file exists**
|
|
64
71
|
- Identify files to create or modify
|
|
65
72
|
- Note dependencies on prior phases
|
|
66
73
|
- Include an estimated scope (small/medium/large)
|
|
67
|
-
|
|
74
|
+
- **When tasks files exist for in-scope features**, respect the `deps:` ordering they declare (no task may be scheduled before its declared deps), and note `[P]`-marked tasks as parallel-safe within a phase so the phase can fan-out work where appropriate
|
|
75
|
+
3. **Account for every unchecked unit of work** — The plan must explicitly place every unchecked capability (or every unchecked task, when a tasks file exists) from in-scope feature PRDs into a phase **or** list it under a "Proposed to Defer" section with a reason. Nothing unchecked may be silently omitted from the plan. The user reviews and approves what gets deferred at plan approval time.
|
|
68
76
|
4. **Define test expectations per phase** — For each phase, specify what tests will be run to verify correctness before moving on (unit tests, integration tests, build verification, etc.)
|
|
69
77
|
5. **Present the plan** — Show the user the full phased plan with clear phase boundaries and ask for approval
|
|
70
78
|
|
|
@@ -113,7 +121,10 @@ Present a brief scaffold summary to the user before proceeding to feature implem
|
|
|
113
121
|
c. **Follow the style** — Apply the design system, tokens, and icon library from `gspec/style.md` or `gspec/style.html` (whichever exists). The style guide is the single authority for icon library choices. Component libraries (e.g., shadcn/ui) are defined in `gspec/stack.md`.
|
|
114
122
|
d. **Match the mockups** — For UI work, if `gspec/design/` contains mockups relevant to the screen or flow you are building, match their layout, spacing, and visual hierarchy. Resolve any conflict between a mockup and the style guide in favor of the style guide's tokens and semantics, then adjust the layout to remain faithful to the mockup's intent. If a mockup shows a visual pattern that the style guide doesn't cover, pause and ask the user whether to extend the style guide or deviate from the mockup.
|
|
115
123
|
e. **Satisfy the requirements** — Trace each piece of code back to a functional requirement in the feature PRD (if available) or to the user's stated goals and the approved implementation plan
|
|
116
|
-
3. **Mark
|
|
124
|
+
3. **Mark progress as you go** — Update checkboxes incrementally, never in a batch at the end. This ensures that if the session is interrupted, progress is not lost.
|
|
125
|
+
- **Tasks (when a tasks file exists)**: as soon as a task is complete and verified, flip its checkbox in `gspec/features/<feature>.tasks.md` from `- [ ]` to `- [x]`.
|
|
126
|
+
- **Capabilities**: flip a PRD capability checkbox from `- [ ]` to `- [x]` only after every task whose `covers:` references it is checked. If no tasks file exists for that feature, flip the capability checkbox immediately on completion (the original behavior). If a capability line did not have a checkbox prefix, add one as `- [x]`.
|
|
127
|
+
- When updating gspec files, preserve existing `spec-version` YAML frontmatter. If a file lacks frontmatter, add `---\nspec-version: v1\n---` at the top.
|
|
117
128
|
4. **Run tests** — Execute the tests defined for this phase (and any existing tests to catch regressions). Fix any failures before proceeding.
|
|
118
129
|
6. **Surface new gaps** — If implementation reveals new ambiguities, pause and consult the user rather than making silent assumptions
|
|
119
130
|
7. **Pause and report** — After completing the phase and confirming tests pass, present a phase completion summary to the user:
|
|
@@ -134,7 +145,7 @@ After implementation:
|
|
|
134
145
|
2. **Review against acceptance criteria** — For each capability in the feature PRDs, check that every acceptance criterion listed under it is satisfied. These sub-listed conditions are the definition of "done" for each capability. If any criterion is not met, the capability should not be marked `[x]`.
|
|
135
146
|
3. **Check the Definition of Done** from `gspec/practices.md`
|
|
136
147
|
4. **Verify no unapproved deferrals** — Compare the final implementation against the approved plan. If any capability that was assigned to a phase was not implemented, **do not silently leave it unchecked**. Flag it to the user, explain why it wasn't completed, and get explicit approval before marking it as deferred. Only capabilities the user approved for deferral during planning (or explicitly approves now) may remain unchecked.
|
|
137
|
-
5. **Verify checkbox accuracy** — Confirm that every capability marked `[x]` in the feature PRDs is genuinely implemented and working. Confirm that capabilities left as `[ ]` were approved for deferral by the user. Present a final status summary:
|
|
148
|
+
5. **Verify checkbox accuracy** — Confirm that every capability marked `[x]` in the feature PRDs is genuinely implemented and working. Confirm that capabilities left as `[ ]` were approved for deferral by the user. **For features with tasks files**, also confirm task↔capability consistency: every checked capability has all its covering tasks checked, and every unchecked capability has at least one unchecked covering task. Present a final status summary:
|
|
138
149
|
|
|
139
150
|
> **Implementation Summary:**
|
|
140
151
|
> - Feature X: 7/7 capabilities implemented (complete)
|
|
@@ -0,0 +1,154 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: gspec-tasks
|
|
3
|
+
description: Decompose a feature PRD in gspec/features/ into an ordered, dependency-aware task plan with parallel-execution markers, written to gspec/features/<feature>.tasks.md. TRIGGER when the user wants to plan execution order, break a feature into tasks, identify what can run in parallel, sequence implementation work, or produce a build plan from a PRD — e.g. "break this feature into tasks", "what order should I build this in", "plan the implementation order", "make a task list for X", "what can run in parallel", "decompose feature Y", "ordered task plan". Run this AFTER gspec-feature and BEFORE gspec-implement when a feature is large or has non-obvious ordering. Prefer this skill over ad-hoc task lists.
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
You are a Senior Engineering Lead at a high-performing software company.
|
|
7
|
+
|
|
8
|
+
Your task is to take a **feature PRD** from `gspec/features/` and decompose it into an **ordered, dependency-aware task plan** with parallel-execution markers. The output is a separate sibling file at `gspec/features/<feature>.tasks.md` that `gspec-implement` consumes during its planning phase.
|
|
9
|
+
|
|
10
|
+
The PRD answers *what* and *why*. The tasks file answers *how* and *in what order*.
|
|
11
|
+
|
|
12
|
+
## When to Run This Skill
|
|
13
|
+
|
|
14
|
+
Run after `gspec-feature` and before `gspec-implement` when:
|
|
15
|
+
|
|
16
|
+
- The feature is large enough that build order matters (more than 3-4 capabilities, or non-trivial cross-capability dependencies)
|
|
17
|
+
- Work could be parallelized and you want that surfaced explicitly
|
|
18
|
+
- You want a reviewable execution plan before code is written
|
|
19
|
+
|
|
20
|
+
Skip this skill for trivial features — `gspec-implement`'s checkbox-driven planning is sufficient there.
|
|
21
|
+
|
|
22
|
+
---
|
|
23
|
+
|
|
24
|
+
## Inputs
|
|
25
|
+
|
|
26
|
+
- **Required**: a feature PRD at `gspec/features/<feature>.md` (the user names the feature; if ambiguous, ask)
|
|
27
|
+
- **Supporting context** (read but don't quote): `gspec/architecture.md`, `gspec/stack.md`. Use these only to inform task granularity and ordering — never to embed project-specific technology choices into the tasks file
|
|
28
|
+
- **Existing tasks file** (if any) at `gspec/features/<feature>.tasks.md` — if present and non-empty, treat it as authoritative state and refuse to overwrite without explicit user confirmation
|
|
29
|
+
|
|
30
|
+
---
|
|
31
|
+
|
|
32
|
+
## Workflow
|
|
33
|
+
|
|
34
|
+
### Phase 1: Discovery
|
|
35
|
+
|
|
36
|
+
1. Read the target feature PRD in full. Extract every capability and its acceptance criteria.
|
|
37
|
+
2. Read `gspec/architecture.md` and `gspec/stack.md` for ordering signals (e.g., schema must exist before API; API before UI).
|
|
38
|
+
3. If a tasks file already exists for this feature, read it. Decide whether the user wants to (a) regenerate from scratch, (b) add tasks for newly added capabilities only, or (c) abort. Ask before proceeding.
|
|
39
|
+
|
|
40
|
+
### Phase 2: Decompose
|
|
41
|
+
|
|
42
|
+
For each unchecked PRD capability:
|
|
43
|
+
|
|
44
|
+
1. Propose **1–N tasks** that, taken together, satisfy the capability's acceptance criteria.
|
|
45
|
+
2. Tasks should be small enough that a single implementation pass can complete and verify each one (typically 1-3 files, 1-3 acceptance criteria worth of work).
|
|
46
|
+
3. Carry the capability's priority (`P0`/`P1`/`P2`) onto each task.
|
|
47
|
+
4. Record the **`covers:` line** verbatim — quote the capability text from the PRD so the trace is unambiguous. A single task may cover multiple capabilities; a single capability may be covered by multiple tasks.
|
|
48
|
+
|
|
49
|
+
### Phase 3: Order & Mark Parallelism
|
|
50
|
+
|
|
51
|
+
1. Identify dependencies. A task depends on another when:
|
|
52
|
+
- It writes files the other reads or extends
|
|
53
|
+
- It uses APIs/types/schemas the other introduces
|
|
54
|
+
- It tests behavior the other implements
|
|
55
|
+
2. Emit a **topological ordering**: list tasks in an order where every `deps:` reference points strictly backwards.
|
|
56
|
+
3. Mark a task `[P]` (parallel-safe) only when it satisfies **both** conditions:
|
|
57
|
+
- Its `deps:` are all already complete (i.e., earlier in the list and not currently in flight beside it)
|
|
58
|
+
- It does not write to the same files as another `[P]`-marked sibling at the same level
|
|
59
|
+
When in doubt, leave `[P]` off. False parallelism causes more pain than missed parallelism.
|
|
60
|
+
|
|
61
|
+
### Phase 4: Plan-Mode Confirmation
|
|
62
|
+
|
|
63
|
+
Enter plan mode and present the proposed tasks file content to the user. Show:
|
|
64
|
+
|
|
65
|
+
- Total task count and how many `[P]`-marked
|
|
66
|
+
- The full proposed file body
|
|
67
|
+
- Any capabilities you could not decompose (explain why)
|
|
68
|
+
- Any cross-feature dependencies you noticed (the user may want to address them in another feature's tasks file)
|
|
69
|
+
|
|
70
|
+
Wait for approval. The user may edit individual tasks, change ordering, drop or add `[P]` markers, or split/merge tasks.
|
|
71
|
+
|
|
72
|
+
### Phase 5: Write
|
|
73
|
+
|
|
74
|
+
After approval, write `gspec/features/<feature>.tasks.md`. Never overwrite a non-empty existing file without explicit user confirmation in Phase 1.
|
|
75
|
+
|
|
76
|
+
When writing, preserve any existing `spec-version` frontmatter from the prior tasks file. New files use `spec-version: v1`.
|
|
77
|
+
|
|
78
|
+
---
|
|
79
|
+
|
|
80
|
+
## Output Format
|
|
81
|
+
|
|
82
|
+
The tasks file has YAML frontmatter and a single `## Tasks` section.
|
|
83
|
+
|
|
84
|
+
```markdown
|
|
85
|
+
---
|
|
86
|
+
spec-version: v1
|
|
87
|
+
feature: <feature-slug>
|
|
88
|
+
---
|
|
89
|
+
|
|
90
|
+
# Tasks: <Feature Name>
|
|
91
|
+
|
|
92
|
+
## Tasks
|
|
93
|
+
|
|
94
|
+
- [ ] **T1** [P] **P0** scaffold the Astro page route at `src/pages/index.astro`
|
|
95
|
+
- deps: —
|
|
96
|
+
- covers: "Page displays a clear tagline and one-line value proposition that communicates what gspec does"
|
|
97
|
+
- [ ] **T2** **P0** wire CTA copy-to-clipboard interaction
|
|
98
|
+
- deps: T1
|
|
99
|
+
- covers: "Page displays a prominent install CTA with the install command"
|
|
100
|
+
- [ ] **T3** [P] **P1** add the workflow diagram component
|
|
101
|
+
- deps: T1
|
|
102
|
+
- covers: "Page explains the gspec workflow in three or fewer steps"
|
|
103
|
+
```
|
|
104
|
+
|
|
105
|
+
### Field rules
|
|
106
|
+
|
|
107
|
+
- **ID**: `T<n>`, monotonically increasing from `T1`. IDs are stable — never renumber existing tasks during a regenerate; append new ones with the next free number.
|
|
108
|
+
- **`[P]`**: optional parallel marker. Place between the ID and the priority.
|
|
109
|
+
- **Priority**: `P0`, `P1`, or `P2`, matching the source capability.
|
|
110
|
+
- **Description**: one short imperative sentence. Concrete files or modules where useful, but no implementation code.
|
|
111
|
+
- **`deps:`**: comma-separated task IDs. Use `—` (em dash) when there are no dependencies.
|
|
112
|
+
- **`covers:`**: capability text from the PRD, quoted. For tasks covering multiple capabilities, separate quoted strings with `; `.
|
|
113
|
+
|
|
114
|
+
### What NOT to write
|
|
115
|
+
|
|
116
|
+
- ❌ No code blocks or pseudocode — that belongs in the implementation step.
|
|
117
|
+
- ❌ No technology choices not already in `stack.md` or `architecture.md`.
|
|
118
|
+
- ❌ No timeline estimates (hours, days, sprints) — see `gspec-feature` for the same rule.
|
|
119
|
+
- ❌ No tasks for capabilities that are already `- [x]` in the PRD, unless the user explicitly requests re-implementation.
|
|
120
|
+
- ❌ No "review" or "documentation" tasks unless the PRD's acceptance criteria explicitly require them.
|
|
121
|
+
|
|
122
|
+
---
|
|
123
|
+
|
|
124
|
+
## Relationship to PRD Checkboxes
|
|
125
|
+
|
|
126
|
+
The tasks file and the PRD use **separate checkboxes**:
|
|
127
|
+
|
|
128
|
+
- **Task checkboxes** (`- [ ]` / `- [x]` in the tasks file) track *execution state* — flip when the task is done.
|
|
129
|
+
- **Capability checkboxes** (`- [ ]` / `- [x]` in the PRD) track *delivery state* — only flip when **every** task whose `covers:` references that capability is complete.
|
|
130
|
+
|
|
131
|
+
`gspec-implement` is responsible for keeping both in sync. This skill only writes the initial unchecked tasks file.
|
|
132
|
+
|
|
133
|
+
---
|
|
134
|
+
|
|
135
|
+
## Output Rules
|
|
136
|
+
|
|
137
|
+
- **Use plan mode** in Phase 4. Never write the tasks file before the user approves.
|
|
138
|
+
- One tasks file per feature. Co-located with the PRD as `gspec/features/<feature>.tasks.md`.
|
|
139
|
+
- Begin each file with the YAML frontmatter shown above.
|
|
140
|
+
- Preserve existing frontmatter and existing task IDs when regenerating — append new tasks rather than renumbering.
|
|
141
|
+
- If you discover the PRD itself is ambiguous (a capability has no clear acceptance criteria), pause and recommend the user run `gspec-feature` to refine the PRD before continuing. Do not invent acceptance criteria.
|
|
142
|
+
|
|
143
|
+
---
|
|
144
|
+
|
|
145
|
+
## Tone & Style
|
|
146
|
+
|
|
147
|
+
- Decisive — pick an ordering and defend it; don't list options.
|
|
148
|
+
- Tight — every task line earns its place.
|
|
149
|
+
- Honest about dependencies — it's better to be slightly conservative on `[P]` than to claim parallelism that doesn't hold.
|
|
150
|
+
|
|
151
|
+
---
|
|
152
|
+
|
|
153
|
+
## Input Feature
|
|
154
|
+
|
package/package.json
CHANGED
package/templates/spec-sync.md
CHANGED
|
@@ -13,6 +13,7 @@ Use this mapping whenever the user's intent matches:
|
|
|
13
13
|
- **Building, implementing, coding, scaffolding, shipping, or "making it real"** — invoke `gspec-implement`. This is the most commonly-missed skill. If the user asks you to write code for anything the specs describe (or a new capability that should be specced), route through `gspec-implement` rather than editing files directly. Generic prompts like "build it", "go", "keep going", "continue", or "do the next phase" should also invoke it when recent conversation has been about specs or planning.
|
|
14
14
|
- **Defining the product, users, or vision** — invoke `gspec-profile`.
|
|
15
15
|
- **Planning or writing a new feature / PRD** — invoke `gspec-feature`.
|
|
16
|
+
- **Producing an ordered task plan from a feature PRD (with explicit dependencies and parallel-execution markers)** — invoke `gspec-tasks`. Run before `gspec-implement` for non-trivial features.
|
|
16
17
|
- **Choosing or revising the tech stack** — invoke `gspec-stack`.
|
|
17
18
|
- **Defining visual design, tokens, or theme** — invoke `gspec-style`.
|
|
18
19
|
- **Setting coding standards, testing, or workflow conventions** — invoke `gspec-practices`.
|
|
@@ -30,7 +31,7 @@ If the user explicitly asks you to skip the skill and just do the work, honor th
|
|
|
30
31
|
|
|
31
32
|
2. **Spec before you build** — If the user asks for a feature or capability that isn't covered by an existing feature PRD in `gspec/features/`, run the `gspec-feature` command to create a new feature PRD before implementing it. Every feature should be specified before it's built — don't skip straight to code.
|
|
32
33
|
|
|
33
|
-
3. **Update feature checkboxes** — When you implement a capability defined in a feature PRD (`gspec/features/*.md`), change its checkbox from `- [ ]` to `- [x]`.
|
|
34
|
+
3. **Update feature checkboxes** — When you implement a capability defined in a feature PRD (`gspec/features/*.md`), change its checkbox from `- [ ]` to `- [x]`. **If a tasks file exists** at `gspec/features/<feature>.tasks.md`, also flip the checkbox of each completed task in that file. Only flip the PRD capability checkbox once every task whose `covers:` references it is checked.
|
|
34
35
|
|
|
35
36
|
4. **Update specs that your changes contradict** — If your code change makes a spec statement incorrect (e.g., you changed the data model, switched a dependency, altered a UI pattern, or added a new API endpoint), update the spec to reflect reality. Common candidates:
|
|
36
37
|
- `gspec/architecture.md` — project structure, data model, API routes, component hierarchy
|