@skitterbyte/skitterspec-jira 2.10.0 → 2.11.0
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/assets/claude-md-section.md +8 -2
- package/assets/commands/allow-project.md +28 -0
- package/assets/core/env.config.md +29 -3
- package/assets/hooks/project-guard.cjs +161 -0
- package/assets/rules/spec-planning.md +32 -1
- package/assets/skills/spec-init/SKILL.md +2 -1
- package/assets/skills/spec-tada/SKILL.md +26 -4
- package/assets/skills/spec-todo/SKILL.md +101 -0
- package/package.json +1 -1
- package/src/cli.js +234 -21
- package/src/env/config.js +19 -3
- package/src/env/hooks.js +10 -0
- package/src/env/integrate.js +5 -34
- package/src/env/live.js +106 -4
- package/src/env/projectguard.js +389 -0
- package/src/env/triggered.js +50 -0
- package/src/tada/digest.js +41 -2
- package/src/tada/format.js +4 -2
- package/src/tada/page.js +35 -7
- package/src/tada/repo.js +22 -2
- package/src/tada/serve.js +13 -7
- package/src/tada/todo.js +245 -0
|
@@ -20,9 +20,15 @@ every phase. **`skitterspec status`** lists what is in flight across worktrees.
|
|
|
20
20
|
At the end of the day, **`/spec-tada`** is the ta-da list: what you did across
|
|
21
21
|
every project, grouped by spec — what landed, what was explored, what is still
|
|
22
22
|
in flight — ending in a three-line standup (`skitterspec tada` is the engine).
|
|
23
|
-
It covers the projects that share this one's `project.category
|
|
23
|
+
It covers the projects that share this one's `project.category`, leads with
|
|
24
|
+
the day's wins, and names only this project's work as the thing to do next;
|
|
24
25
|
**`skitterspec project`** shows and sets the name and category, and
|
|
25
|
-
`/spec-init` asks for both.
|
|
26
|
+
`/spec-init` asks for both. In the morning, **`/spec-todo`** answers the other
|
|
27
|
+
question: where each project was left on your last working day, what is
|
|
28
|
+
waiting on you, and what to pick up first. Both read across projects, and
|
|
29
|
+
neither acts on one: a session works on the project it was started in, and a
|
|
30
|
+
hook refuses its writes and lifecycle commands anywhere else until you type
|
|
31
|
+
`/allow-project <name>`.
|
|
26
32
|
|
|
27
33
|
**Handing the review back.** The page takes marks: tick `✓ accept` per file as
|
|
28
34
|
you read, note anything against a line or a whole file, answer the questions a
|
|
@@ -0,0 +1,28 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: Let this session work on another skitterspec project — name it (or its path); `off` guards it again
|
|
3
|
+
argument-hint: "<project> [off]"
|
|
4
|
+
allowed-tools: Bash({{exec}} skitterspec spec-env project allow:*)
|
|
5
|
+
disable-model-invocation: true
|
|
6
|
+
---
|
|
7
|
+
!`{{exec}} skitterspec spec-env project allow $ARGUMENTS`
|
|
8
|
+
|
|
9
|
+
Relay the engine output above verbatim. Add nothing and run nothing else.
|
|
10
|
+
|
|
11
|
+
**Only you can run this, and that is the whole guard.** The project-guard hook
|
|
12
|
+
refuses a write, a `git` change or a `skitterspec` lifecycle command aimed at a
|
|
13
|
+
skitterspec project other than the one this session was started in. Its refusal
|
|
14
|
+
names two exits: open a session in that project and do the work there, or have
|
|
15
|
+
you lift the guard. Claude can take the first and can never take the second — a
|
|
16
|
+
guard the model can lift is decoration, which is the line `/allow-main` draws.
|
|
17
|
+
|
|
18
|
+
**Name the project the refusal named.** `/allow-project ereqs` lifts it for that
|
|
19
|
+
folder name; a path (`/allow-project ../ereqs`) pins it to that exact repo.
|
|
20
|
+
|
|
21
|
+
**It lapses with the session.** The lift is recorded against this session, so
|
|
22
|
+
a new session is guarded again. Where the harness exposes no session id it
|
|
23
|
+
degrades to a repo-wide lift that lasts until `/allow-project <project> off`;
|
|
24
|
+
the engine says which kind you got.
|
|
25
|
+
|
|
26
|
+
**It is machine-local and gitignored.** The project-wide switch is
|
|
27
|
+
`guards.projectBoundary` in `specs/.core/env.config.json`, and turning that off
|
|
28
|
+
is a different, committed decision.
|
|
@@ -5,7 +5,7 @@ stack + host dev servers + a front-door proxy per in-progress spec).
|
|
|
5
5
|
Provisioning is folded into `/spec-start`, teardown into `/spec-complete` ·
|
|
6
6
|
`/spec-cancel`, traffic diversion is `/spec-connect`, and reading a spec's diff
|
|
7
7
|
is `/spec-diff`; the `skitterspec spec-env
|
|
8
|
-
<up|bootstrap|nospec|main|down|prune|dev|connect|integrate|disposition|handoff|hotfix|live|review|stage|status|resolve|base>` CLI is
|
|
8
|
+
<up|bootstrap|nospec|main|project|down|prune|dev|connect|integrate|disposition|handoff|hotfix|live|review|stage|status|resolve|base>` CLI is
|
|
9
9
|
the engine beneath them.
|
|
10
10
|
|
|
11
11
|
**Once this file is present, isolation is the default policy:** `/spec-start` gives
|
|
@@ -376,9 +376,17 @@ through to a documented conservative default; see the field notes below.
|
|
|
376
376
|
// blocks when the commits are ALSO unmerged into the base branch — a branch
|
|
377
377
|
// already landed on base tears down (and its branch is deleted) without
|
|
378
378
|
// --force, even with no remote.
|
|
379
|
+
//
|
|
380
|
+
// `projectBoundary` (default true): a session works on the project it was
|
|
381
|
+
// started in. The project-guard hook refuses a write, a git change or a
|
|
382
|
+
// skitterspec lifecycle command aimed at ANOTHER skitterspec project (a
|
|
383
|
+
// checkout with specs/.core/); reads and every other program pass. The user
|
|
384
|
+
// lifts it for one session with /allow-project <name>; false turns it off
|
|
385
|
+
// for this project. Its sibling `mainIsLandingZone` is the main guard's switch.
|
|
379
386
|
"guards": {
|
|
380
387
|
"refuseTeardownIfDirty": true,
|
|
381
|
-
"refuseTeardownIfUnpushed": true
|
|
388
|
+
"refuseTeardownIfUnpushed": true,
|
|
389
|
+
"projectBoundary": true
|
|
382
390
|
},
|
|
383
391
|
|
|
384
392
|
// What teardown cleans up beyond this machine. Nothing publishes a spec
|
|
@@ -416,8 +424,26 @@ through to a documented conservative default; see the field notes below.
|
|
|
416
424
|
// Under `land.strategy: "pr"` take fetches and rebases onto
|
|
417
425
|
// `<land.remote>/<base>`, since local base moves only when you pull; a
|
|
418
426
|
// failed fetch falls back to local base and says so.
|
|
427
|
+
//
|
|
428
|
+
// `afterSwitch` is `afterLand`'s grammar — a string, `{ "run", "when" }`, or
|
|
429
|
+
// `{ "setup": true }` — run in the PRIMARY checkout after `live take` checks
|
|
430
|
+
// the branch out, and again after `live release` switches back. Both decide
|
|
431
|
+
// `when` against the same files (what the branch changes from base), since
|
|
432
|
+
// release reverts what take brought in. Unlike `afterLand` the ENGINE runs
|
|
433
|
+
// these, because `/spec-live` and the page's live action have no caller turn
|
|
434
|
+
// to run anything after them: output is captured, the first failure stops the
|
|
435
|
+
// list with the tail of its output, and the switch is never undone.
|
|
436
|
+
// A separate list, not `afterLand`, because `afterLand` may hold a data
|
|
437
|
+
// migration, which must never run for a branch that has not landed:
|
|
438
|
+
//
|
|
439
|
+
// "afterSwitch": [{ "setup": true }]
|
|
440
|
+
//
|
|
441
|
+
// [] (or absent) = none, and take and release print what they always did. It
|
|
442
|
+
// does not replace the "restart your dev server" warning — an install is not
|
|
443
|
+
// a restart.
|
|
419
444
|
"live": {
|
|
420
|
-
"migrations": []
|
|
445
|
+
"migrations": [],
|
|
446
|
+
"afterSwitch": []
|
|
421
447
|
},
|
|
422
448
|
|
|
423
449
|
// Hotfix landing (`spec-env hotfix land` / `/spec-complete` on a Type: Hotfix
|
|
@@ -0,0 +1,161 @@
|
|
|
1
|
+
#!/usr/bin/env node
|
|
2
|
+
'use strict'
|
|
3
|
+
|
|
4
|
+
/**
|
|
5
|
+
* Project guard — the harness half.
|
|
6
|
+
*
|
|
7
|
+
* A session belongs to the project it was started in. The skills say so, and a
|
|
8
|
+
* skill is prose: a report that ends on another repo's `/spec-complete` reads
|
|
9
|
+
* as an instruction, and nothing in prose stops a session `cd`-ing over there
|
|
10
|
+
* and doing it. So the rule is also enforced one level down, where a write or a
|
|
11
|
+
* shell command is a tool call the harness has to ask about first.
|
|
12
|
+
*
|
|
13
|
+
* WHAT IT GUARDS: a write tool whose path lands in another skitterspec project,
|
|
14
|
+
* and a Bash command that runs `git` (to change something) or the engine there.
|
|
15
|
+
* Reads, and every other program, pass.
|
|
16
|
+
*
|
|
17
|
+
* THIS SCRIPT DECIDES NOTHING. It hands the call to `spec-env project check`
|
|
18
|
+
* and turns one exit status into an answer, for `main-guard.cjs`'s reason: a
|
|
19
|
+
* hook with its own opinions is a second implementation nothing can test.
|
|
20
|
+
*
|
|
21
|
+
* HOME IS THIS SCRIPT'S PROJECT, NOT THE SESSION'S DIRECTORY. `cwd` is wherever
|
|
22
|
+
* the session has `cd`-ed to — which is exactly the thing being judged — so the
|
|
23
|
+
* project this hook was installed into is the one the session belongs to.
|
|
24
|
+
*
|
|
25
|
+
* IT FAILS OPEN, EVERYWHERE: no engine, an unreadable payload, a crash, a
|
|
26
|
+
* timeout. Being wrong the permissive way costs one act the skills also warn
|
|
27
|
+
* against; being wrong the other way stops ordinary work with no reason given.
|
|
28
|
+
*/
|
|
29
|
+
|
|
30
|
+
const fs = require('node:fs')
|
|
31
|
+
const path = require('node:path')
|
|
32
|
+
const { spawnSync } = require('node:child_process')
|
|
33
|
+
|
|
34
|
+
function allow() {
|
|
35
|
+
process.exit(0)
|
|
36
|
+
}
|
|
37
|
+
|
|
38
|
+
// The JSON route rather than exit-2, so the reason reaches Claude — who has to
|
|
39
|
+
// act on it by leaving the work to a session in that project.
|
|
40
|
+
function deny(reason) {
|
|
41
|
+
process.stdout.write(
|
|
42
|
+
JSON.stringify({
|
|
43
|
+
hookSpecificOutput: {
|
|
44
|
+
hookEventName: 'PreToolUse',
|
|
45
|
+
permissionDecision: 'deny',
|
|
46
|
+
permissionDecisionReason: reason,
|
|
47
|
+
},
|
|
48
|
+
}) + '\n',
|
|
49
|
+
)
|
|
50
|
+
process.exit(0)
|
|
51
|
+
}
|
|
52
|
+
|
|
53
|
+
function readPayload() {
|
|
54
|
+
try {
|
|
55
|
+
const parsed = JSON.parse(fs.readFileSync(0, 'utf8'))
|
|
56
|
+
return parsed && typeof parsed === 'object' ? parsed : null
|
|
57
|
+
} catch {
|
|
58
|
+
return null
|
|
59
|
+
}
|
|
60
|
+
}
|
|
61
|
+
|
|
62
|
+
// Identical to `main-guard.cjs`'s, deliberately — see the reasons there.
|
|
63
|
+
const ENGINES = ['skitterspec', 'skitterspec-linear', 'skitterspec-jira', 'skitterspec-github', 'skitterspec-azure-boards']
|
|
64
|
+
|
|
65
|
+
function findEngine(projectDir, platform = process.platform) {
|
|
66
|
+
if (process.env.SKITTERSPEC_BIN) return process.env.SKITTERSPEC_BIN
|
|
67
|
+
let at = projectDir
|
|
68
|
+
for (let i = 0; i < 6 && at; i++) {
|
|
69
|
+
for (const name of ENGINES) {
|
|
70
|
+
const candidate =
|
|
71
|
+
platform === 'win32'
|
|
72
|
+
? path.join(at, 'node_modules', '@skitterbyte', name, 'bin', `${name}.js`)
|
|
73
|
+
: path.join(at, 'node_modules', '.bin', name)
|
|
74
|
+
if (fs.existsSync(candidate)) return candidate
|
|
75
|
+
}
|
|
76
|
+
const up = path.dirname(at)
|
|
77
|
+
if (up === at) break
|
|
78
|
+
at = up
|
|
79
|
+
}
|
|
80
|
+
return 'skitterspec'
|
|
81
|
+
}
|
|
82
|
+
|
|
83
|
+
function engineCommand(projectDir, platform = process.platform) {
|
|
84
|
+
const engine = findEngine(projectDir, platform)
|
|
85
|
+
return /\.[cm]?js$/i.test(engine) ? { file: process.execPath, args: [engine] } : { file: engine, args: [] }
|
|
86
|
+
}
|
|
87
|
+
|
|
88
|
+
const WRITE_TOOLS = new Set(['Edit', 'Write', 'NotebookEdit', 'MultiEdit'])
|
|
89
|
+
|
|
90
|
+
function writeTarget(input) {
|
|
91
|
+
if (!input || typeof input !== 'object') return null
|
|
92
|
+
for (const key of ['file_path', 'notebook_path']) {
|
|
93
|
+
if (typeof input[key] === 'string' && input[key]) return input[key]
|
|
94
|
+
}
|
|
95
|
+
return null
|
|
96
|
+
}
|
|
97
|
+
|
|
98
|
+
// A command that cannot be one the guard is about — no git, no engine — is let
|
|
99
|
+
// through without starting the engine at all. This hook fires on every Bash
|
|
100
|
+
// call, and most of them are neither.
|
|
101
|
+
function mayConcern(command) {
|
|
102
|
+
return /\bgit\b|skitterspec/.test(command)
|
|
103
|
+
}
|
|
104
|
+
|
|
105
|
+
// Inside the home checkout itself: certainly home, no engine needed. A
|
|
106
|
+
// worktree lives elsewhere, so a path outside this is still asked about.
|
|
107
|
+
function insideHome(home, target) {
|
|
108
|
+
const rel = path.relative(home, path.resolve(home, target))
|
|
109
|
+
return rel === '' || (!rel.startsWith('..') && !path.isAbsolute(rel))
|
|
110
|
+
}
|
|
111
|
+
|
|
112
|
+
function isRefusal(stdout) {
|
|
113
|
+
return /^spec-env project: /m.test(stdout || '')
|
|
114
|
+
}
|
|
115
|
+
|
|
116
|
+
function homeDir() {
|
|
117
|
+
// `${CLAUDE_PROJECT_DIR}` is the project the harness started in; the script's
|
|
118
|
+
// own location is the same answer when it is not set.
|
|
119
|
+
return process.env.CLAUDE_PROJECT_DIR || path.resolve(__dirname, '..', '..')
|
|
120
|
+
}
|
|
121
|
+
|
|
122
|
+
function main() {
|
|
123
|
+
const payload = readPayload()
|
|
124
|
+
if (!payload) allow()
|
|
125
|
+
|
|
126
|
+
const home = homeDir()
|
|
127
|
+
const cwd = typeof payload.cwd === 'string' && payload.cwd ? payload.cwd : process.cwd()
|
|
128
|
+
const session = typeof payload.session_id === 'string' ? payload.session_id : ''
|
|
129
|
+
const argv = ['spec-env', 'project', 'check', '--dir', home, '--cwd', cwd]
|
|
130
|
+
|
|
131
|
+
if (WRITE_TOOLS.has(payload.tool_name)) {
|
|
132
|
+
const target = writeTarget(payload.tool_input)
|
|
133
|
+
if (!target || insideHome(home, path.resolve(cwd, target))) allow()
|
|
134
|
+
argv.push('--path', path.resolve(cwd, target))
|
|
135
|
+
} else if (payload.tool_name === 'Bash') {
|
|
136
|
+
const command = payload.tool_input && payload.tool_input.command
|
|
137
|
+
if (typeof command !== 'string' || !mayConcern(command)) allow()
|
|
138
|
+
argv.push('--command', command)
|
|
139
|
+
} else {
|
|
140
|
+
allow()
|
|
141
|
+
}
|
|
142
|
+
if (session) argv.push('--session', session)
|
|
143
|
+
|
|
144
|
+
const engine = engineCommand(home)
|
|
145
|
+
const result = spawnSync(engine.file, [...engine.args, ...argv], { cwd: home, encoding: 'utf8', timeout: 8000 })
|
|
146
|
+
if (result.error || result.status !== 1) allow()
|
|
147
|
+
// Exit 1 alone is a crash as often as a refusal; the printed line decides.
|
|
148
|
+
const said = (result.stdout || '').trim()
|
|
149
|
+
if (!isRefusal(said)) allow()
|
|
150
|
+
deny(said)
|
|
151
|
+
}
|
|
152
|
+
|
|
153
|
+
if (require.main === module) {
|
|
154
|
+
try {
|
|
155
|
+
main()
|
|
156
|
+
} catch {
|
|
157
|
+
allow()
|
|
158
|
+
}
|
|
159
|
+
}
|
|
160
|
+
|
|
161
|
+
module.exports = { findEngine, engineCommand, WRITE_TOOLS, writeTarget, mayConcern, insideHome, isRefusal }
|
|
@@ -21,6 +21,7 @@ and lifecycle stay consistent. Each sets a status on the spec header
|
|
|
21
21
|
| `/spec-complete` | Verify all phases done + tests green; land + tear down | `Complete` | `specs/complete/` |
|
|
22
22
|
| `/spec-cancel` | Record progress, stamp a reason on the header; tear down | `Cancelled` | `specs/cancelled/` |
|
|
23
23
|
| `/spec-tada` | A ta-da list — recap what you did in Claude Code over a window, across every project, by project then spec, ending in a standup. Read-only | (unchanged) | (unchanged) |
|
|
24
|
+
| `/spec-todo` | The morning half — where each project was left on the last working day, what is waiting on you, what to pick up first. Read-only | (unchanged) | (unchanged) |
|
|
24
25
|
| `/spec-init` | Bootstrap/repair this workflow in a project (idempotent) | — | — |
|
|
25
26
|
|
|
26
27
|
**Skills vs commands.** The table above lists **skills** — Claude reads them and
|
|
@@ -84,6 +85,17 @@ by a branch that happens to contain it — a spec branch cut this afternoon
|
|
|
84
85
|
contains all of this morning. It is model-invocable, because "what did I do
|
|
85
86
|
today?" should reach it.
|
|
86
87
|
|
|
88
|
+
**It leads with the wins, and it acts on nothing outside home.** The digest
|
|
89
|
+
marks a completed bug, hotfix or incident as `★ saved bacon` and any other
|
|
90
|
+
completed spec or a cut release as `★ win`, so the evening answer to *did I get
|
|
91
|
+
anything done?* opens with the evidence. It also marks the project the run
|
|
92
|
+
started from as `(here)`, and the report's closing `Next` — the line a reader
|
|
93
|
+
copies — names only that project's work: other projects' next steps are
|
|
94
|
+
suggestions in their own sections. **`/spec-todo`** is the morning half
|
|
95
|
+
(`skitterspec todo`): the last day with any activity, up to 14 days back, each
|
|
96
|
+
open spec where it was left, the verdicts waiting and gates armed, and today
|
|
97
|
+
so far — home first, and listed even when nothing happened there.
|
|
98
|
+
|
|
87
99
|
**A report covers one category.** `project.category` in `env.config.json`
|
|
88
100
|
decides which projects share a report — only those with the category of the
|
|
89
101
|
repo it runs from, and an uncategorised project is in nobody's but its own
|
|
@@ -131,6 +143,21 @@ the guard, and only a person can type it. That asymmetry is the same line
|
|
|
131
143
|
`/spec-reviewed` draws, and `spec-planning.md` already records that prose alone
|
|
132
144
|
did not hold it once.
|
|
133
145
|
|
|
146
|
+
**`/allow-project` is its twin, for the other direction.** The main guard
|
|
147
|
+
stops work landing where it should not happen; `.claude/hooks/project-guard.cjs`
|
|
148
|
+
stops a session doing work that is **not its project's**. A session belongs to
|
|
149
|
+
the project it was started in, and a report read across projects once ended on
|
|
150
|
+
another repo's `/spec-complete` — which the session ran, `cd`-ing over there to
|
|
151
|
+
do it. So a write, a `git` change or a `skitterspec` lifecycle command aimed at
|
|
152
|
+
another skitterspec project (a checkout with `specs/.core/`) is refused, while
|
|
153
|
+
reads (`git log`, `skitterspec tada`) and every other program pass. Home is the
|
|
154
|
+
project the hook is installed in, never the session's cwd, because after a `cd`
|
|
155
|
+
the cwd is the thing being judged. `skitterspec spec-env project
|
|
156
|
+
<check|allow|status>` is the engine, `guards.projectBoundary` turns it off, and
|
|
157
|
+
it fails open on every cannot-tell. `/allow-project <name>` lifts it for one
|
|
158
|
+
session, and it is user-only for `/allow-main`'s reason: Claude must not be
|
|
159
|
+
able to lift a guard aimed at Claude.
|
|
160
|
+
|
|
134
161
|
**`/spec-skip` is the fifth command**, and it is user-only for `/allow-main`'s
|
|
135
162
|
reason rather than the mild one: it lifts the review gate, which is a guard
|
|
136
163
|
aimed at Claude. It pre-executes `skitterspec spec-env review skip "<reason>"`
|
|
@@ -214,7 +241,7 @@ your canonical `localhost` ports so you can test it at the normal URL
|
|
|
214
241
|
move, header edits, the code) happens on the spec's branch in the worktree; `main`
|
|
215
242
|
changes only when it merges. Teardown is folded into `/spec-complete` ·
|
|
216
243
|
`/spec-cancel`. Beneath the skills, `skitterspec spec-env
|
|
217
|
-
<up|bootstrap|nospec|main|down|prune|dev|connect|integrate|disposition|handoff|hotfix|live|review|stage|status|resolve|base>` is the CLI
|
|
244
|
+
<up|bootstrap|nospec|main|project|down|prune|dev|connect|integrate|disposition|handoff|hotfix|live|review|stage|status|resolve|base>` is the CLI
|
|
218
245
|
engine. `up` plans the fork;
|
|
219
246
|
**`bootstrap` then runs the worktree's own steps itself** — seeding the gitignored files, the env file, `setup`, the stack — so
|
|
220
247
|
the command a skill runs names no file, and a secrets hook that refuses any
|
|
@@ -249,6 +276,10 @@ thumb: **live overlay is the light default for *testing* a code-only spec** —
|
|
|
249
276
|
is not how work gets started, and no lifecycle skill invokes it; it *refuses*
|
|
250
277
|
stateful ones (`Stack: worktree + docker`, or a branch touching migrations) — keep
|
|
251
278
|
`/spec-connect` + a Docker stack for those, and for genuinely parallel testing.
|
|
279
|
+
`live.afterSwitch` is the switch's counterpart of `afterLand` — the same
|
|
280
|
+
`{ run, when }` entries, run in the primary checkout after take and again after
|
|
281
|
+
release, so a changed lockfile or schema is caught up both ways. The engine runs
|
|
282
|
+
them itself, since `/spec-live` has no turn to run anything after it.
|
|
252
283
|
Beneath it, `skitterspec spec-env live <take|release|abort|status>` is the engine.
|
|
253
284
|
|
|
254
285
|
**Authoring a spec is work, so it happens off the base branch too (`/spec`).**
|
|
@@ -27,7 +27,7 @@ clobber customised content. Finish with a summary of created vs already-present.
|
|
|
27
27
|
> **Leave alone**. Non-interactively it only adds what's missing; `--resync` /
|
|
28
28
|
> `--reset` (reset needs `--yes`) drive the stronger actions.
|
|
29
29
|
|
|
30
|
-
The system is **
|
|
30
|
+
The system is **seventeen skills**: `spec` (feature, chore or issue), `spec-bug` (bug),
|
|
31
31
|
`spec-hotfix` (a bug fixed on a released tag),
|
|
32
32
|
`spec-incident` (a live outage, recorded as it happens),
|
|
33
33
|
`no-spec` (work that genuinely has none — off the base branch all the same),
|
|
@@ -36,6 +36,7 @@ The system is **sixteen skills**: `spec` (feature, chore or issue), `spec-bug` (
|
|
|
36
36
|
`spec-reviewed` (pick up a review you approved on that page),
|
|
37
37
|
`spec-epic-next` (name the epic member that can start now), `spec-to-main`,
|
|
38
38
|
`spec-complete`, `spec-cancel`, `spec-tada` (a ta-da list of what got done),
|
|
39
|
+
`spec-todo` (where you left off, and what is ahead),
|
|
39
40
|
and this `spec-init`. The lifecycle is `backlog → in-progress → complete / cancelled`,
|
|
40
41
|
with `.core` holding always-apply project rules.
|
|
41
42
|
|
|
@@ -69,6 +69,15 @@ do not paste it anywhere else, and never publish it.
|
|
|
69
69
|
|
|
70
70
|
## 2. Write the recap
|
|
71
71
|
|
|
72
|
+
**Open with the wins.** The evening question this answers is usually *did I
|
|
73
|
+
get anything done?*, and the answer is nearly always more than it felt like.
|
|
74
|
+
Before the projects, a short **Wins** list from the digest's `★` lines:
|
|
75
|
+
`★ saved bacon` (a bug, hotfix or incident finished — something was broken and
|
|
76
|
+
now is not) first, then `★ win` (a spec completed, a release cut). You may
|
|
77
|
+
promote **one** more from the prompts — a long fight with one problem that
|
|
78
|
+
ended in a fix, say — and only with its evidence in the same line. Never
|
|
79
|
+
invent one, and leave the section out on a day with none.
|
|
80
|
+
|
|
72
81
|
One section per project, then one entry per group. A group headed by a spec
|
|
73
82
|
(`feat-orders [#12]`) is that spec's work wherever it happened — its branch, its
|
|
74
83
|
worktree, or a commit on the base naming it. A group headed `<branch> — no spec`
|
|
@@ -88,6 +97,14 @@ For each group, say what applies and skip what does not:
|
|
|
88
97
|
- **In flight** — the `in flight:` line: where the spec stands and its next
|
|
89
98
|
action, as the engine wrote it.
|
|
90
99
|
|
|
100
|
+
**Only the `(here)` project's next actions are commands.** The project marked
|
|
101
|
+
`(here)` is the one this session was started in, and it is the only one this
|
|
102
|
+
session acts on. For every other project, say where it stands as a suggestion
|
|
103
|
+
in its own section — *"ereqs has chore-perf-alerts ready to complete"* — never
|
|
104
|
+
as a bare `/spec-…` command. A command at the bottom of a report is what gets
|
|
105
|
+
copied and run, and running it from here means working on another repo from a
|
|
106
|
+
session that does not belong to it.
|
|
107
|
+
|
|
91
108
|
Name a spec by its folder and its ticket exactly as the digest gives them. Keep
|
|
92
109
|
each entry to a line or two; a project with only in-flight rows gets one line
|
|
93
110
|
listing them.
|
|
@@ -95,9 +112,13 @@ listing them.
|
|
|
95
112
|
Then the **standup** — three lines, no more:
|
|
96
113
|
|
|
97
114
|
- **Done:** the work that landed or moved, across every project.
|
|
98
|
-
- **Next:** the in-flight next actions that matter most
|
|
99
|
-
|
|
100
|
-
|
|
115
|
+
- **Next:** the `(here)` project's in-flight next actions that matter most —
|
|
116
|
+
or `nothing in flight here`.
|
|
117
|
+
- **Blockers:** the `(here)` project's — a verdict waiting, a gate armed, a
|
|
118
|
+
wait unmet — or `none`. Only what the digest shows; never invent one.
|
|
119
|
+
|
|
120
|
+
**A quiet today points at the morning.** Run with no window flag and nothing
|
|
121
|
+
in it, say once in `Notes` that `/spec-todo` answers *where did I leave off*.
|
|
101
122
|
|
|
102
123
|
## 3. The page — only when asked
|
|
103
124
|
|
|
@@ -147,7 +168,8 @@ what is specific here.
|
|
|
147
168
|
page's tiers (or its `file://` path) when one was rendered. `Notes` carries the digest's own closing
|
|
148
169
|
lines (`cannot tell`, torn-down worktrees counted elsewhere) and, when no page
|
|
149
170
|
was asked for, that `--page` renders one. `Next` is the one
|
|
150
|
-
in-flight action the standup put first
|
|
171
|
+
in-flight action the standup put first — the `(here)` project's, never
|
|
172
|
+
another's — or `nothing in flight here`.
|
|
151
173
|
|
|
152
174
|
**`Follow-ups` is always `none` here.** This skill reports work; anything it
|
|
153
175
|
notices belongs to the spec it is about.
|
|
@@ -0,0 +1,101 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: spec-todo
|
|
3
|
+
description: The morning half of the ta-da list — where each project was left on the last day you worked (Monday reads Friday), what is still open, what is waiting on you, and what to pick up first, ending in a three-line standup. Read-only. Use when the user says "/spec-todo", "where did I leave off", "what's on today", "what was I doing", "morning summary", or starts a day asking what is next.
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
# /spec-todo — where you left off, and what is ahead
|
|
7
|
+
|
|
8
|
+
> Stay silent while this runs — speak only to ask something you cannot answer
|
|
9
|
+
> yourself, or to report a failure at the moment it happens. Read
|
|
10
|
+
> `.claude/rules/spec-reports.md` before reporting; it defines the block this
|
|
11
|
+
> skill ends with.
|
|
12
|
+
|
|
13
|
+
Read-only. It writes nothing, commits nothing and publishes nothing. `/spec-tada`
|
|
14
|
+
answers the evening question — *did I get anything done?* — and this answers the
|
|
15
|
+
morning one: *where was I, and what now?*
|
|
16
|
+
|
|
17
|
+
## 1. Get the to-do
|
|
18
|
+
|
|
19
|
+
```
|
|
20
|
+
skitterspec todo [--here | --all-projects]
|
|
21
|
+
```
|
|
22
|
+
|
|
23
|
+
- **`--here`** — "this repo", "this project": only the repo the session is
|
|
24
|
+
standing in.
|
|
25
|
+
- **`--all-projects`** — "everything", "work and personal": every project on the
|
|
26
|
+
machine.
|
|
27
|
+
|
|
28
|
+
There is no window to choose. The engine finds the **last day with any activity**
|
|
29
|
+
before today — up to 14 days back, so a Monday reads Friday and a day off is
|
|
30
|
+
skipped — and reads that day, plus today so far. It is scoped by
|
|
31
|
+
`project.category` exactly as `/spec-tada` is, and names the category on its
|
|
32
|
+
first line when there is one.
|
|
33
|
+
|
|
34
|
+
**Read the text form, never `--json`**, and **never read a transcript yourself** —
|
|
35
|
+
the same two rules, for the same reasons, as `/spec-tada`. The output quotes the
|
|
36
|
+
person's own prompts; it stays in this conversation and is never published.
|
|
37
|
+
|
|
38
|
+
What the lines mean:
|
|
39
|
+
|
|
40
|
+
- `(here)` — the project this session was started in. It is listed first, and
|
|
41
|
+
it is listed even on a morning nothing happened there, with its open specs.
|
|
42
|
+
- `left:` — the last move or commit on that spec, the day it was left.
|
|
43
|
+
- `- …` — the last thing typed on it: what was on the person's mind when they
|
|
44
|
+
stopped.
|
|
45
|
+
- `in flight:` — where the spec stands now, and its next action.
|
|
46
|
+
- `finished:` — the specs that day completed or cancelled, by name.
|
|
47
|
+
- `blocked:` — a review verdict waiting, or a gate armed by a phase that ended
|
|
48
|
+
and still owes an answer. Read only for specs in flight.
|
|
49
|
+
- `today:` — commits and moves since midnight, when there are any.
|
|
50
|
+
|
|
51
|
+
## 2. Write the recap
|
|
52
|
+
|
|
53
|
+
One short section per project, `(here)` first. For each open spec, one line:
|
|
54
|
+
where it was left and what is next, in plain words. Then `finished:` as one line
|
|
55
|
+
and `blocked:` lines as they are — a blocker is the thing most worth seeing in
|
|
56
|
+
the morning.
|
|
57
|
+
|
|
58
|
+
**Only the `(here)` project's next actions are commands.** Every other project's
|
|
59
|
+
are suggestions in its own section — *"ereqs has chore-perf-alerts ready to
|
|
60
|
+
complete"* — never a bare `/spec-…`. This session acts on the project it was
|
|
61
|
+
started in; the others are picked up in a session of their own.
|
|
62
|
+
|
|
63
|
+
Then the **standup** — three lines, no more:
|
|
64
|
+
|
|
65
|
+
- **Left off:** where yesterday (or the last working day) ended, across every
|
|
66
|
+
project — a line, not a list.
|
|
67
|
+
- **Today:** the `(here)` project's first one or two actions — or
|
|
68
|
+
`nothing in flight here`.
|
|
69
|
+
- **Blockers:** the `(here)` project's `blocked:` lines — or `none`. Only what
|
|
70
|
+
the output shows; never invent one.
|
|
71
|
+
|
|
72
|
+
A fortnight with nothing in it is still an answer: say so, and name what is in
|
|
73
|
+
flight in the home project if anything is.
|
|
74
|
+
|
|
75
|
+
## 3. The page — only when asked
|
|
76
|
+
|
|
77
|
+
Exactly as `/spec-tada` §3, with `skitterspec todo <the same flags> --page
|
|
78
|
+
--summary <that file>`. It is served beside the ta-da page where the project has
|
|
79
|
+
a review server, and is a `file://` page where it does not. Never publish it.
|
|
80
|
+
|
|
81
|
+
## Report
|
|
82
|
+
|
|
83
|
+
The recap and standup are the body of the message; the block follows them and
|
|
84
|
+
is the last thing in it.
|
|
85
|
+
|
|
86
|
+
**Verdicts**
|
|
87
|
+
|
|
88
|
+
- `✅` — the to-do is written. Nothing in 14 days is still `✅`, said as such.
|
|
89
|
+
- `⚠️` — written, but the output said `cannot tell` somewhere. Name it in
|
|
90
|
+
`Notes`.
|
|
91
|
+
|
|
92
|
+
**Fields:** `Built` · `Notes` · `Follow-ups` · `Next`
|
|
93
|
+
|
|
94
|
+
`Built` is the day it read as "left off" and the counts — projects, open specs,
|
|
95
|
+
blockers — and the page's tiers (or its `file://` path) when one was rendered.
|
|
96
|
+
`Notes` carries the output's own closing lines and, when no page was asked for,
|
|
97
|
+
that `--page` renders one. `Next` is the `(here)` project's first action, or
|
|
98
|
+
`nothing in flight here` — never another project's.
|
|
99
|
+
|
|
100
|
+
**`Follow-ups` is always `none` here.** This skill reports work; anything it
|
|
101
|
+
notices belongs to the spec it is about.
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@skitterbyte/skitterspec-jira",
|
|
3
|
-
"version": "2.
|
|
3
|
+
"version": "2.11.0",
|
|
4
4
|
"description": "Spec-driven development for Claude Code, with one-way Jira Cloud sync — a superset of @skitterbyte/skitterspec: the base filesystem workflow plus /spec-status · /spec-push and the spec-sync CLI. The repo is canonical; Jira is a generated mirror. Install this OR the base OR the Linear superset — exactly one.",
|
|
5
5
|
"keywords": [
|
|
6
6
|
"claude",
|