completion-check

Name: completion-check
Author: parcadei

468installs297forks

How to install completion-check?

parcadei/continuous-claude-v3/completion-check

$npx -y skills add parcadei/Continuous-Claude-v3 --skill completion-check

Installs into the current project.

Summary

Completion Check: Verify Infrastructure Is Wired

Files · 1

View on GitHub

SKILL.md

1	# Completion Check: Verify Infrastructure Is Wired
2
3	When building infrastructure, verify it's actually connected to the system before marking as complete.
4
5	## Pattern
6
7	Infrastructure is not done when the code is written - it's done when it's wired into the system and actively used. Dead code (built but never called) is wasted effort.
8
9	## DO
10
11	1. Trace the execution path - Follow from user intent to actual code execution:
12	```bash
13	# Example: Verify Task tool spawns correctly
14	grep -r "claude -p" src/
15	grep -r "Task(" src/
16	```
17
18	2. Check hooks are registered, not just implemented:
19	```bash
20	# Hook exists?
21	ls -la .claude/hooks/my-hook.sh
22
23	# Hook registered in settings?
24	grep "my-hook" .claude/settings.json
25	```
26
27	3. Verify database connections - Ensure infrastructure uses the right backend:
28	```bash
29	# Check connection strings
30	grep -r "postgresql://" src/
31	grep -r "sqlite:" src/ # Should NOT find if PostgreSQL expected
32	```
33
34	4. Test end-to-end - Run the feature and verify infrastructure is invoked:
35	```bash
36	# Add debug logging
37	echo "DEBUG: DAG spawn invoked" >> /tmp/debug.log
38
39	# Trigger feature
40	uv run python -m my_feature
41
42	# Verify infrastructure was called
43	cat /tmp/debug.log
44	```
45
46	5. Search for orphaned implementations:
47	```bash
48	# Find functions defined but never called
49	ast-grep --pattern 'async function $NAME() { $$$ }' \| \
50	xargs -I {} grep -r "{}" src/
51	```
52
53	## DON'T
54
55	- Mark infrastructure "complete" without testing execution path
56	- Assume code is wired just because it exists
57	- Build parallel systems (Task tool vs claude -p spawn)
58	- Use wrong backends (SQLite when PostgreSQL is architected)
59	- Skip end-to-end testing ("it compiles" ≠ "it runs")
60
61	## Completion Checklist
62
63	Before declaring infrastructure complete:
64
65	- [ ] Traced execution path from entry point to infrastructure
66	- [ ] Verified hooks are registered in .claude/settings.json
67	- [ ] Confirmed correct database/backend in use
68	- [ ] Ran end-to-end test showing infrastructure invoked
69	- [ ] Searched for dead code or parallel implementations
70	- [ ] Checked configuration files match implementation
71
72	## Example: DAG Task Graph
73
74	Wrong approach:
75	```
76	✓ Built BeadsTaskGraph class
77	✓ Implemented DAG dependencies
78	✓ Added spawn logic
79	✗ Never wired - Task tool still runs instead
80	✗ Used SQLite instead of PostgreSQL
81	```
82
83	Right approach:
84	```
85	✓ Built BeadsTaskGraph class
86	✓ Wired into Task tool execution path
87	✓ Verified claude -p spawn is called
88	✓ Confirmed PostgreSQL backend in use
89	✓ Tested: user calls Task() → DAG spawns → beads execute
90	✓ No parallel implementations found
91	```
92
93	## Source Sessions
94
95	- This session: Architecture gap discovery - DAG built but not wired, Task tool runs instead of spawn, SQLite used instead of PostgreSQL

People who liked this also viewed

6 picks

Type

tddSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026501k181k
test-driven-developmentUse when implementing any feature or bugfix, before writing implementation codeSkillsJul 2026175k259k
qaSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026160k181k
verification-before-completionUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidenceSkillsJul 2026153k259k
webapp-testingToolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser lSkillsJul 2026120k163k
playwright-best-practicesUse when writing Playwright tests, fixing flaky tests, debugging failures, implementing Page Object Model, configuring CI/CD, optimizing performance, mocking APIs, handling authentication or OAuth, teSkillsJul 202664k338

completion-check

468installs297forks

View on GitHub

How to install completion-check?

parcadei/continuous-claude-v3/completion-check

$npx -y skills add parcadei/Continuous-Claude-v3 --skill completion-check

Installs into the current project.

Summary

Completion Check: Verify Infrastructure Is Wired

Files · 1

View on GitHub

SKILL.md

1	# Completion Check: Verify Infrastructure Is Wired
2
3	When building infrastructure, verify it's actually connected to the system before marking as complete.
4
5	## Pattern
6
7	Infrastructure is not done when the code is written - it's done when it's wired into the system and actively used. Dead code (built but never called) is wasted effort.
8
9	## DO
10
11	1. Trace the execution path - Follow from user intent to actual code execution:
12	```bash
13	# Example: Verify Task tool spawns correctly
14	grep -r "claude -p" src/
15	grep -r "Task(" src/
16	```
17
18	2. Check hooks are registered, not just implemented:
19	```bash
20	# Hook exists?
21	ls -la .claude/hooks/my-hook.sh
22
23	# Hook registered in settings?
24	grep "my-hook" .claude/settings.json
25	```
26
27	3. Verify database connections - Ensure infrastructure uses the right backend:
28	```bash
29	# Check connection strings
30	grep -r "postgresql://" src/
31	grep -r "sqlite:" src/ # Should NOT find if PostgreSQL expected
32	```
33
34	4. Test end-to-end - Run the feature and verify infrastructure is invoked:
35	```bash
36	# Add debug logging
37	echo "DEBUG: DAG spawn invoked" >> /tmp/debug.log
38
39	# Trigger feature
40	uv run python -m my_feature
41
42	# Verify infrastructure was called
43	cat /tmp/debug.log
44	```
45
46	5. Search for orphaned implementations:
47	```bash
48	# Find functions defined but never called
49	ast-grep --pattern 'async function $NAME() { $$$ }' \| \
50	xargs -I {} grep -r "{}" src/
51	```
52
53	## DON'T
54
55	- Mark infrastructure "complete" without testing execution path
56	- Assume code is wired just because it exists
57	- Build parallel systems (Task tool vs claude -p spawn)
58	- Use wrong backends (SQLite when PostgreSQL is architected)
59	- Skip end-to-end testing ("it compiles" ≠ "it runs")
60
61	## Completion Checklist
62
63	Before declaring infrastructure complete:
64
65	- [ ] Traced execution path from entry point to infrastructure
66	- [ ] Verified hooks are registered in .claude/settings.json
67	- [ ] Confirmed correct database/backend in use
68	- [ ] Ran end-to-end test showing infrastructure invoked
69	- [ ] Searched for dead code or parallel implementations
70	- [ ] Checked configuration files match implementation
71
72	## Example: DAG Task Graph
73
74	Wrong approach:
75	```
76	✓ Built BeadsTaskGraph class
77	✓ Implemented DAG dependencies
78	✓ Added spawn logic
79	✗ Never wired - Task tool still runs instead
80	✗ Used SQLite instead of PostgreSQL
81	```
82
83	Right approach:
84	```
85	✓ Built BeadsTaskGraph class
86	✓ Wired into Task tool execution path
87	✓ Verified claude -p spawn is called
88	✓ Confirmed PostgreSQL backend in use
89	✓ Tested: user calls Task() → DAG spawns → beads execute
90	✓ No parallel implementations found
91	```
92
93	## Source Sessions
94
95	- This session: Architecture gap discovery - DAG built but not wired, Task tool runs instead of spawn, SQLite used instead of PostgreSQL

People who liked this also viewed

6 picks

Type