hk-local-diagnose

Name: hk-local-diagnose
Author: deepklarity

84stars12forks

How to install hk-local-diagnose?

deepklarity/harness-kit/hk-local-diagnose

$npx -y skills add deepklarity/harness-kit --skill hk-local-diagnose

Installs into the current project.

Summary

Run diagnostic scripts on tasks, specs, boards, or reflections. Wraps testing_tools/ with proper working directory and output mode selection. Use this skill whenever the user wants to inspect, debug, or check the state of a task, spec, board, or reflection — even if they don't sa

Files · 1

View on GitHub

SKILL.md

1	# /hk-local-diagnose — Diagnostic Script Runner
2
3	Run the right diagnostic script with the right flags, from the right directory. No more remembering paths or cd-ing around.
4
5	## Usage
6
7	```
8	/hk-local-diagnose task 42
9	/hk-local-diagnose task 42 --brief
10	/hk-local-diagnose spec 15 --json --sections tasks,problems
11	/hk-local-diagnose board
12	/hk-local-diagnose board 3
13	/hk-local-diagnose reflection 8 --full
14	/hk-local-diagnose snapshot sp25 ../../tests/e2e_snapshots/smoke
15	```
16
17	## Arguments
18
19	Parse `$ARGUMENTS` to extract:
20	- type (required): `task`, `spec`, `board`, `reflection`, or `snapshot`
21	- id (required for all except `board`): the numeric ID or spec prefix
22	- flags (optional): `--brief`, `--full`, `--json`, `--slim`, `--sections <list>`
23
24	If no flags are provided, default to `--brief` — this is the token-efficient choice for LLM consumption. The user can always ask for `--full` if they need more.
25
26	## Script mapping
27
28	\| Type \| Script \| Required args \|
29	\|------\|--------\|---------------\|
30	\| `task` \| `task_inspect.py <id>` \| id \|
31	\| `spec` \| `spec_trace.py <id>` \| id \|
32	\| `board` \| `board_overview.py [id]` \| id optional \|
33	\| `reflection` \| `reflection_inspect.py <id>` \| id \|
34	\| `snapshot` \| `snapshot_extractor.py <id> <output_dir>` \| id + output_dir \|
35
36	## Execution
37
38	All scripts run from the `taskit/taskit-backend/` directory. The working directory for execution is always:
39
40	```
41	REPO_ROOT/taskit/taskit-backend/
42	```
43
44	Where `REPO_ROOT` is the git repository root (find it with `git rev-parse --show-toplevel`).
45
46	### Step 1: Resolve the repo root
47
48	```bash
49	REPO_ROOT=$(git rev-parse --show-toplevel)
50	```
51
52	### Step 2: Build and run the command
53
54	```bash
55	cd "$REPO_ROOT/taskit/taskit-backend" && python testing_tools/<script> <id> [flags]
56	```
57
58	Pass through any `--brief`, `--full`, `--json`, `--slim`, or `--sections` flags directly to the script.
59
60	### Step 3: Display the output
61
62	Print the script output directly. Do not summarize or interpret — the scripts already produce well-structured output with problem detection built in.
63
64	If the script exits with a non-zero code, show the error and suggest:
65	- Check that the ID exists: "Is task/spec/board {id} a valid ID?"
66	- Check that the Django app is set up: "Is the taskit-backend database accessible?"
67
68	## Error handling
69
70	If `$ARGUMENTS` is empty or missing the type, print usage help:
71
72	```
73	Usage: /hk-local-diagnose <type> <id> [flags]
74
75	Types: task, spec, board, reflection, snapshot
76	Flags: --brief (default), --full, --json, --slim, --sections <list>
77
78	Examples:
79	/hk-local-diagnose task 42
80	/hk-local-diagnose spec 15 --json --sections tasks,problems
81	/hk-local-diagnose board
82	```

People who liked this also viewed

6 picks

Type

hk-local-diagnose

84stars12forks

View on GitHub

How to install hk-local-diagnose?

deepklarity/harness-kit/hk-local-diagnose

$npx -y skills add deepklarity/harness-kit --skill hk-local-diagnose

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# /hk-local-diagnose — Diagnostic Script Runner
2
3	Run the right diagnostic script with the right flags, from the right directory. No more remembering paths or cd-ing around.
4
5	## Usage
6
7	```
8	/hk-local-diagnose task 42
9	/hk-local-diagnose task 42 --brief
10	/hk-local-diagnose spec 15 --json --sections tasks,problems
11	/hk-local-diagnose board
12	/hk-local-diagnose board 3
13	/hk-local-diagnose reflection 8 --full
14	/hk-local-diagnose snapshot sp25 ../../tests/e2e_snapshots/smoke
15	```
16
17	## Arguments
18
19	Parse `$ARGUMENTS` to extract:
20	- type (required): `task`, `spec`, `board`, `reflection`, or `snapshot`
21	- id (required for all except `board`): the numeric ID or spec prefix
22	- flags (optional): `--brief`, `--full`, `--json`, `--slim`, `--sections <list>`
23
24	If no flags are provided, default to `--brief` — this is the token-efficient choice for LLM consumption. The user can always ask for `--full` if they need more.
25
26	## Script mapping
27
28	\| Type \| Script \| Required args \|
29	\|------\|--------\|---------------\|
30	\| `task` \| `task_inspect.py <id>` \| id \|
31	\| `spec` \| `spec_trace.py <id>` \| id \|
32	\| `board` \| `board_overview.py [id]` \| id optional \|
33	\| `reflection` \| `reflection_inspect.py <id>` \| id \|
34	\| `snapshot` \| `snapshot_extractor.py <id> <output_dir>` \| id + output_dir \|
35
36	## Execution
37
38	All scripts run from the `taskit/taskit-backend/` directory. The working directory for execution is always:
39
40	```
41	REPO_ROOT/taskit/taskit-backend/
42	```
43
44	Where `REPO_ROOT` is the git repository root (find it with `git rev-parse --show-toplevel`).
45
46	### Step 1: Resolve the repo root
47
48	```bash
49	REPO_ROOT=$(git rev-parse --show-toplevel)
50	```
51
52	### Step 2: Build and run the command
53
54	```bash
55	cd "$REPO_ROOT/taskit/taskit-backend" && python testing_tools/<script> <id> [flags]
56	```
57
58	Pass through any `--brief`, `--full`, `--json`, `--slim`, or `--sections` flags directly to the script.
59
60	### Step 3: Display the output
61
62	Print the script output directly. Do not summarize or interpret — the scripts already produce well-structured output with problem detection built in.
63
64	If the script exits with a non-zero code, show the error and suggest:
65	- Check that the ID exists: "Is task/spec/board {id} a valid ID?"
66	- Check that the Django app is set up: "Is the taskit-backend database accessible?"
67
68	## Error handling
69
70	If `$ARGUMENTS` is empty or missing the type, print usage help:
71
72	```
73	Usage: /hk-local-diagnose <type> <id> [flags]
74
75	Types: task, spec, board, reflection, snapshot
76	Flags: --brief (default), --full, --json, --slim, --sections <list>
77
78	Examples:
79	/hk-local-diagnose task 42
80	/hk-local-diagnose spec 15 --json --sections tasks,problems
81	/hk-local-diagnose board
82	```

People who liked this also viewed

6 picks

Type