@codyswann/lisa 1.6.0 → 1.7.1

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.
@@ -7,38 +7,22 @@ Complete all of the following steps for $ARGUMENTS:
7
7
 
8
8
  ## Step 1: Setup
9
9
 
10
- Run `/project:setup $ARGUMENTS` directly (not via Task tool).
11
- - Creates project directory, brief.md, findings.md, git branch
12
- - Creates `.claude-active-project` marker file
13
- - Outputs the project name (e.g., `2026-01-26-my-feature`)
10
+ Run `/project:setup $ARGUMENTS`
14
11
 
15
12
  Capture the project name from the output for use in subsequent steps.
16
13
 
17
- ## Step 2: Create and Execute Tasks
14
+ ## Step 2: Research
18
15
 
19
- Create workflow tracking tasks with `metadata.project` set to the project name from Step 1:
16
+ Run `/project:research @projects/<project-name>`
20
17
 
21
- ```
22
- TaskCreate:
23
- subject: "Research project requirements"
24
- description: "Run /project:research projects/<project-name> to gather codebase and web research."
25
- metadata: { project: "<project-name-from-step-1>" }
18
+ ## Step 3: Gap Detection
26
19
 
27
- TaskCreate:
28
- subject: "Gap detection and execution"
29
- description: "Read projects/<project-name>/research.md. Check '## Open Questions' section. If unresolved questions exist, STOP and report to human. If no gaps, immediately run /project:execute @projects/<project-name>"
30
- metadata: { project: "<project-name-from-step-1>" }
31
- ```
20
+ Read @projects/<project-name>/research.md.
32
21
 
33
- **Execute each task via a subagent** to preserve main context. Launch up to 6 in parallel where tasks don't have dependencies. Do not stop until both are completed.
22
+ Check '## Open Questions' section. If unresolved questions exist, STOP and report to human.
23
+
24
+ If no gaps, immediately run `/project:execute @projects/<project-name>`
34
25
 
35
26
  ## Output to Human
36
27
 
37
28
  - If gaps exist: "⚠️ Bootstrap complete but needs human review - see Open Questions in research.md"
38
- - If no gaps: Execution will begin automatically
39
-
40
- ---
41
-
42
- ## Next Step
43
-
44
- After completing this phase, tell the user: "To continue, run `/project:execute @projects/<project-name>`"
@@ -40,10 +40,4 @@ TaskCreate:
40
40
  - Are simple "never do X" or "always do Y" statements
41
41
  - Cannot be scoped to a skill that's invoked on-demand
42
42
 
43
- If a learning only applies to certain types of work (e.g., "when writing GraphQL resolvers..."), it should be a **skill** instead, not a rule.
44
-
45
- ---
46
-
47
- ## Next Step
48
-
49
- After completing this phase, tell the user: "To continue, run `/project:archive $ARGUMENTS`"
43
+ If a learning only applies to certain types of work (e.g., "when writing GraphQL resolvers..."), it should be a **skill** instead, not a rule.
@@ -0,0 +1,51 @@
1
+ ---
2
+ description: Updates all documentation related to changes implemented in the project
3
+ argument-hint: <project-directory>
4
+ allowed-tools: Read, Write, Edit, Bash, Glob, Grep, Task, TaskCreate, TaskUpdate, TaskList, Skill
5
+ ---
6
+
7
+ The current branch is a feature branch with implementation of the project in $ARGUMENTS.
8
+
9
+ Changes on this branch need corresponding documentation updates to keep README, API docs, changelogs, and JSDoc current.
10
+
11
+ **IMPORTANT**: Perform each step and move to the next without stopping.
12
+
13
+ ## Setup
14
+
15
+ Set active project marker: `echo "$ARGUMENTS" | sed 's|.*/||' > .claude-active-project`
16
+
17
+ Extract `<project-name>` from the last segment of `$ARGUMENTS`.
18
+
19
+ ## Create and Execute Tasks
20
+
21
+ Create workflow tracking tasks with `metadata.project` set to the project name:
22
+
23
+ ```
24
+ TaskCreate:
25
+ subject: "Identify changed files and documentation targets"
26
+ description: "Use git to identify files changed on this branch (git diff main...HEAD --name-only). For each changed file, identify related documentation: README sections, API docs, inline JSDoc, CHANGELOG entries, architecture docs, configuration docs. Compile a mapping of: changed file → related documentation file(s). Save to $ARGUMENTS/doc-targets.json with structure: { \"file.ts\": [\"README.md#section\", \"docs/api.md\"], ... }"
27
+ metadata: { project: "<project-name>" }
28
+
29
+ TaskCreate:
30
+ subject: "Update README and user-facing docs"
31
+ description: "For each documentation target in $ARGUMENTS/doc-targets.json that is a README section or user guide: Read the changed implementation file. Read the current documentation section. Update the documentation to accurately reflect the new/changed behavior, examples, or configuration. Preserve existing structure and tone."
32
+ metadata: { project: "<project-name>" }
33
+
34
+ TaskCreate:
35
+ subject: "Update API and technical documentation"
36
+ description: "For each documentation target that is API docs, architecture docs, or technical guides: Read the changed implementation. Read the current documentation. Update to reflect new endpoints, parameters, type signatures, behavior changes, or architectural decisions. Ensure consistency with code comments."
37
+ metadata: { project: "<project-name>" }
38
+
39
+ TaskCreate:
40
+ subject: "Update CHANGELOG"
41
+ description: "If CHANGELOG.md or CHANGELOG.{md,txt,rst} exists in project root: Add entry for all user-facing changes. Group by type (Added, Changed, Fixed, Deprecated). Reference relevant files or features. Follow existing CHANGELOG format and conventions."
42
+ metadata: { project: "<project-name>" }
43
+
44
+ TaskCreate:
45
+ subject: "Verify JSDoc on changed files"
46
+ description: "Read $ARGUMENTS/doc-targets.json. For each changed file (key), verify its JSDoc preamble and function/export documentation are current: Run /jsdoc-best-practices skill. Check that file-level preambles explain the module's purpose and when to use it. Check that exported functions/types have 'why' documentation (not just 'what'). Update any stale or missing documentation."
47
+ metadata: { project: "<project-name>" }
48
+ ```
49
+
50
+ **Execute each task via a subagent** to preserve main context. Launch up to 5 in parallel where tasks don't have dependencies. Do not stop until all are completed.
51
+
@@ -41,6 +41,11 @@ TaskCreate:
41
41
  description: "Run /project:review $ARGUMENTS to review code changes."
42
42
  metadata: { project: "<project-name>" }
43
43
 
44
+ TaskCreate:
45
+ subject: "Documentation"
46
+ description: "Run /project:document $ARGUMENTS to update documentation related to changes."
47
+ metadata: { project: "<project-name>" }
48
+
44
49
  TaskCreate:
45
50
  subject: "Verification"
46
51
  description: "Run /project:verify $ARGUMENTS to verify all requirements are met."
@@ -60,9 +65,3 @@ TaskCreate:
60
65
  **Execute each task via a subagent** to preserve main context. Launch up to 6 in parallel where tasks don't have dependencies. Do not stop until all are completed.
61
66
 
62
67
  Report "Project complete and archived" when done.
63
-
64
- ---
65
-
66
- ## Next Step
67
-
68
- The project workflow is now complete. The implementation is done, reviewed, verified, learnings captured, and the project is archived.
@@ -171,9 +171,3 @@ Use **TaskList** to show the created tasks.
171
171
  ---
172
172
 
173
173
  **IMPORTANT**: Each task description should contain all necessary information from `brief.md` and `research.md` to complete in isolation. Tasks should be independent and as small in scope as possible.
174
-
175
- ---
176
-
177
- ## Next Step
178
-
179
- After completing this phase, tell the user: "To continue, run `/project:implement $ARGUMENTS`"
@@ -163,9 +163,3 @@ Run `/git:commit`
163
163
  - Focus on finding concrete file paths and line numbers
164
164
  - Each sub-agent prompt should be specific and focused on read-only documentation
165
165
  - **REMEMBER**: Document what IS, not what SHOULD BE
166
-
167
- ---
168
-
169
- ## Next Step
170
-
171
- After completing this phase, tell the user: "To continue, run `/project:plan $ARGUMENTS`"
@@ -46,9 +46,3 @@ TaskCreate:
46
46
  ```
47
47
 
48
48
  **Execute each task via a subagent** to preserve main context. Launch up to 6 in parallel where tasks don't have dependencies. Do not stop until all are completed.
49
-
50
- ---
51
-
52
- ## Next Step
53
-
54
- After completing this phase, tell the user: "To continue, run `/project:verify $ARGUMENTS`"
@@ -39,9 +39,3 @@ TaskCreate:
39
39
  ```
40
40
 
41
41
  **Execute each task via a subagent** to preserve main context. Launch up to 6 in parallel where tasks don't have dependencies. Do not stop until all are completed.
42
-
43
- ---
44
-
45
- ## Next Step
46
-
47
- After completing this phase, tell the user: "To continue, run `/project:debrief $ARGUMENTS`"
package/package.json CHANGED
@@ -80,7 +80,7 @@
80
80
  "@ast-grep/cli"
81
81
  ],
82
82
  "name": "@codyswann/lisa",
83
- "version": "1.6.0",
83
+ "version": "1.7.1",
84
84
  "description": "Claude Code governance framework that applies guardrails, guidance, and automated enforcement to projects",
85
85
  "main": "dist/index.js",
86
86
  "bin": {