@hasna/assistants 1.1.97 → 1.1.98

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.
@@ -0,0 +1,46 @@
1
+ ---
2
+ name: codereview
3
+ description: Review code for bugs, security issues, performance problems, and style. Accepts a file path, diff, or inline code snippet.
4
+ argument-hint: [file-path-or-diff]
5
+ allowed-tools: Read, Bash
6
+ ---
7
+
8
+ ## Code Review
9
+
10
+ Review the following for: $ARGUMENTS
11
+
12
+ ### What to look for
13
+
14
+ 1. **Bugs & correctness** — logic errors, off-by-one, null/undefined handling, edge cases, incorrect assumptions
15
+ 2. **Security** — injection risks (SQL, shell, XSS), hardcoded secrets, insecure defaults, improper input validation, path traversal
16
+ 3. **Performance** — N+1 queries, unnecessary re-renders, blocking operations, missing indexes, large allocations
17
+ 4. **Readability** — unclear naming, overly complex logic that could be simplified, missing or misleading comments
18
+ 5. **Error handling** — swallowed errors, missing error boundaries, unclear error messages
19
+ 6. **Type safety** — `any` types, unsafe casts, missing nullability checks
20
+
21
+ ### Process
22
+
23
+ 1. If `$ARGUMENTS` is a file path, read the file first with the Read tool
24
+ 2. If it's a glob or directory, read the relevant files
25
+ 3. If it's inline code, review it directly
26
+ 4. For each issue found, state: **location** → **severity** (critical/high/medium/low) → **problem** → **fix**
27
+
28
+ ### Output format
29
+
30
+ ```
31
+ ## Code Review: <file or description>
32
+
33
+ ### Critical
34
+ - [line X] <issue> → <fix>
35
+
36
+ ### High
37
+ - [line X] <issue> → <fix>
38
+
39
+ ### Medium / Low
40
+ - <issue> → <fix>
41
+
42
+ ### Summary
43
+ <1-2 sentence overall assessment>
44
+ ```
45
+
46
+ If no issues are found, say so explicitly — don't pad with non-issues.
@@ -0,0 +1,41 @@
1
+ ---
2
+ name: commitmsg
3
+ description: Generate a conventional commit message from staged changes or a diff. Follows Conventional Commits spec (feat/fix/chore/refactor/docs/test/perf/ci).
4
+ argument-hint: [optional: file paths or description]
5
+ allowed-tools: Bash
6
+ ---
7
+
8
+ ## Generate Commit Message
9
+
10
+ $ARGUMENTS
11
+
12
+ ### Process
13
+
14
+ 1. Run `git diff --staged` to see staged changes (or `git diff HEAD` if nothing staged)
15
+ 2. If `$ARGUMENTS` mentions specific files, focus on those
16
+ 3. Analyse what changed — what was added, removed, modified, and why
17
+ 4. Generate a commit message following Conventional Commits
18
+
19
+ ### Conventional Commits format
20
+
21
+ ```
22
+ <type>(<scope>): <short summary>
23
+
24
+ <optional body: what changed and why, wrapped at 72 chars>
25
+
26
+ <optional footer: BREAKING CHANGE: ..., Closes #123>
27
+ ```
28
+
29
+ **Types:** `feat` (new feature), `fix` (bug fix), `perf` (performance), `refactor` (no behaviour change), `docs` (documentation only), `test` (tests only), `chore` (tooling/deps), `ci` (CI/CD), `style` (formatting)
30
+
31
+ **Rules:**
32
+ - Subject line ≤ 72 characters, imperative mood ("add X" not "added X")
33
+ - Scope is optional but useful (e.g. `feat(auth):`, `fix(cli):`)
34
+ - Body explains *why*, not *what* (the diff shows what)
35
+ - Mark breaking changes with `BREAKING CHANGE:` in footer
36
+ - Reference issues with `Closes #N` or `Fixes #N`
37
+
38
+ ### Output
39
+
40
+ Print the ready-to-use commit message in a code block so it can be copied directly.
41
+ If the changes span multiple unrelated concerns, suggest splitting into separate commits.
@@ -0,0 +1,59 @@
1
+ ---
2
+ name: debug
3
+ description: Structured debugging session. Accepts an error message, stack trace, or description of unexpected behaviour. Works through reproduce → isolate → hypothesize → verify → fix.
4
+ argument-hint: [error message or description]
5
+ allowed-tools: Bash, Read, Grep
6
+ ---
7
+
8
+ ## Debug Session
9
+
10
+ **Problem:** $ARGUMENTS
11
+
12
+ ### Step 1 — Understand the error
13
+
14
+ - Parse the error message and stack trace
15
+ - Identify the failing file, line, and function
16
+ - Note what was expected vs. what actually happened
17
+
18
+ ### Step 2 — Reproduce
19
+
20
+ - Find the minimal steps or input that trigger the issue
21
+ - Run the failing command / test to confirm the error is present
22
+ - Note exact error output
23
+
24
+ ### Step 3 — Isolate
25
+
26
+ - Narrow down to the smallest code path involved
27
+ - Check recent changes (`git log --oneline -10`, `git diff HEAD~1`) — did something recently break this?
28
+ - Search for related error messages or similar patterns in the codebase
29
+
30
+ ### Step 4 — Hypothesize
31
+
32
+ - List 2–3 plausible root causes, ranked by likelihood
33
+ - For each hypothesis, state what evidence would confirm or rule it out
34
+
35
+ ### Step 5 — Verify
36
+
37
+ - Test each hypothesis by reading relevant code, adding debug output, or running targeted commands
38
+ - Eliminate hypotheses one by one until the root cause is confirmed
39
+
40
+ ### Step 6 — Fix
41
+
42
+ - Implement the minimal correct fix
43
+ - Verify the fix resolves the original error
44
+ - Check for related issues the fix might cause
45
+ - Add a regression note if useful
46
+
47
+ ### Output format
48
+
49
+ Work through each step out loud. Show commands run and their output. End with:
50
+ ```
51
+ ## Root cause
52
+ <one sentence>
53
+
54
+ ## Fix applied
55
+ <what was changed>
56
+
57
+ ## Verified by
58
+ <how you confirmed it works>
59
+ ```