com um clique
skill-latex-implementation
// Implement LaTeX documents following a plan. Invoke for LaTeX-language implementation tasks.
// Implement LaTeX documents following a plan. Invoke for LaTeX-language implementation tasks.
Create scoped git commits for task operations. Invoke after task status changes or artifact creation.
Execute general implementation tasks following a plan. Invoke for non-Lean implementation work.
Research and develop semantic theories using ModelChecker with Z3 SMT solver. Define operators, adjust frame constraints, create examples, run tests, and report findings. Invoke with /mc or when working with model-checker, semantic theories, or Z3 constraints.
Route commands to appropriate workflows based on task language and status. Invoke when executing /task, /research, /plan, /implement commands.
Create phased implementation plans from research findings. Invoke when a task needs an implementation plan.
Research Python/Z3 patterns and APIs for semantic theory development. Invoke for Python-language research tasks.
| name | skill-latex-implementation |
| description | Implement LaTeX documents following a plan. Invoke for LaTeX-language implementation tasks. |
| allowed-tools | Task, Bash, Edit, Read, Write |
Thin wrapper that delegates LaTeX document implementation to latex-implementation-agent subagent.
IMPORTANT: This skill implements the skill-internal postflight pattern. After the subagent returns, this skill handles all postflight operations (status update, artifact linking, git commit) before returning. This eliminates the "continue" prompt issue between skill return and orchestrator.
Reference (do not load eagerly):
.claude/context/core/formats/return-metadata-file.md - Metadata file schema.claude/context/core/patterns/postflight-control.md - Marker file protocol.claude/context/core/patterns/file-metadata-exchange.md - File I/O helpers.claude/context/core/patterns/jq-escaping-workarounds.md - jq escaping patterns (Issue #1132)Note: This skill is a thin wrapper with internal postflight. Context is loaded by the delegated agent.
This skill activates when:
Before delegating to the subagent, update task status to "implementing".
Reference: @.claude/context/core/patterns/inline-status-update.md
Update state.json:
jq --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" \
--arg status "implementing" \
--arg sid "$session_id" \
'(.active_projects[] | select(.project_number == '$task_number')) |= . + {
status: $status,
last_updated: $ts,
session_id: $sid,
started: $ts
}' specs/state.json > /tmp/state.json && mv /tmp/state.json specs/state.json
Update TODO.md: Use Edit tool to change status marker from [PLANNED] to [IMPLEMENTING].
Update plan file (if exists): Update the Status field in plan metadata:
# Find latest plan file (use padded directory number)
padded_num=$(printf "%03d" "$task_number")
plan_file=$(ls -1 "specs/${padded_num}_${project_name}/plans/implementation-"*.md 2>/dev/null | sort -V | tail -1)
if [ -n "$plan_file" ] && [ -f "$plan_file" ]; then
sed -i "s/^\- \*\*Status\*\*: \[.*\]$/- **Status**: [IMPLEMENTING]/" "$plan_file"
fi
Create Postflight Marker:
# Ensure task directory exists
mkdir -p "specs/${padded_num}_${project_name}"
cat > "specs/${padded_num}_${project_name}/.postflight-pending" << EOF
{
"session_id": "${session_id}",
"skill": "skill-latex-implementation",
"task_number": ${task_number},
"operation": "implement",
"reason": "Postflight pending: status update, artifact linking, git commit",
"created": "$(date -u +%Y-%m-%dT%H:%M:%SZ)",
"stop_hook_active": false
}
EOF
Validate required inputs:
task_number - Must be provided and exist in state.json# Lookup task
task_data=$(jq -r --arg num "$task_number" \
'.active_projects[] | select(.project_number == ($num | tonumber))' \
specs/state.json)
# Validate exists
if [ -z "$task_data" ]; then
return error "Task $task_number not found"
fi
# Extract fields
language=$(echo "$task_data" | jq -r '.language // "general"')
status=$(echo "$task_data" | jq -r '.status')
project_name=$(echo "$task_data" | jq -r '.project_name')
description=$(echo "$task_data" | jq -r '.description // ""')
# Validate language
if [ "$language" != "latex" ]; then
return error "Task $task_number is not a LaTeX task"
fi
# Validate status
if [ "$status" = "completed" ]; then
return error "Task already completed"
fi
Prepare delegation context:
{
"session_id": "sess_{timestamp}_{random}",
"delegation_depth": 1,
"delegation_path": ["orchestrator", "implement", "skill-latex-implementation"],
"timeout": 3600,
"task_context": {
"task_number": N,
"task_name": "{project_name}",
"description": "{description}",
"language": "latex"
},
"plan_path": "specs/{NNN}_{SLUG}/plans/implementation-{NNN}.md",
"metadata_file_path": "specs/{NNN}_{SLUG}/.return-meta.json"
}
CRITICAL: You MUST use the Task tool to spawn the subagent.
The agent field in this skill's frontmatter specifies the target: latex-implementation-agent
Required Tool Invocation:
Tool: Task (NOT Skill)
Parameters:
- subagent_type: "latex-implementation-agent"
- prompt: [Include task_context, delegation_context, plan_path]
- description: "Execute LaTeX implementation for task {N}"
DO NOT use Skill(latex-implementation-agent) - this will FAIL.
Agents live in .claude/agents/, not .claude/skills/.
The Skill tool can only invoke skills from .claude/skills/.
The subagent will:
specs/{NNN}_{SLUG}/.return-meta.jsonIMPORTANT: Check if subagent accidentally returned JSON to console (v1 pattern) instead of writing to file (v2 pattern).
If the subagent's text return parses as valid JSON, log a warning:
# Check if subagent return looks like JSON (starts with { and is valid JSON)
subagent_return="$SUBAGENT_TEXT_RETURN"
if echo "$subagent_return" | grep -q '^{' && echo "$subagent_return" | jq empty 2>/dev/null; then
echo "WARNING: Subagent returned JSON to console instead of writing metadata file."
echo "This indicates the agent may have outdated instructions (v1 pattern instead of v2)."
echo "The skill will continue by reading the metadata file, but this should be fixed."
fi
This validation:
After subagent returns, read the metadata file:
metadata_file="specs/${padded_num}_${project_name}/.return-meta.json"
if [ -f "$metadata_file" ] && jq empty "$metadata_file" 2>/dev/null; then
status=$(jq -r '.status' "$metadata_file")
artifact_path=$(jq -r '.artifacts[0].path // ""' "$metadata_file")
artifact_type=$(jq -r '.artifacts[0].type // ""' "$metadata_file")
artifact_summary=$(jq -r '.artifacts[0].summary // ""' "$metadata_file")
phases_completed=$(jq -r '.metadata.phases_completed // 0' "$metadata_file")
phases_total=$(jq -r '.metadata.phases_total // 0' "$metadata_file")
# Extract completion_data fields (if present)
completion_summary=$(jq -r '.completion_data.completion_summary // ""' "$metadata_file")
roadmap_items=$(jq -c '.completion_data.roadmap_items // []' "$metadata_file")
else
echo "Error: Invalid or missing metadata file"
status="failed"
fi
Validate the metadata contains required fields:
After implementation, update task status based on result.
Reference: @.claude/context/core/patterns/inline-status-update.md
If result.status == "implemented":
Update state.json to "completed" and add completion_data fields (two-step pattern for Issue #1132):
# Step 1: Update status and timestamps
jq --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" \
--arg status "completed" \
'(.active_projects[] | select(.project_number == '$task_number')) |= . + {
status: $status,
last_updated: $ts,
completed: $ts
}' specs/state.json > /tmp/state.json && mv /tmp/state.json specs/state.json
# Step 2: Add completion_summary (always required for completed tasks)
if [ -n "$completion_summary" ]; then
jq --arg summary "$completion_summary" \
'(.active_projects[] | select(.project_number == '$task_number')).completion_summary = $summary' \
specs/state.json > /tmp/state.json && mv /tmp/state.json specs/state.json
fi
# Step 3: Add roadmap_items (if present and non-empty)
if [ "$roadmap_items" != "[]" ] && [ -n "$roadmap_items" ]; then
jq --argjson items "$roadmap_items" \
'(.active_projects[] | select(.project_number == '$task_number')).roadmap_items = $items' \
specs/state.json > /tmp/state.json && mv /tmp/state.json specs/state.json
fi
# Step 4: Filter out existing summary artifacts (use "| not" pattern to avoid != escaping - Issue #1132)
jq '(.active_projects[] | select(.project_number == '$task_number')).artifacts =
[(.active_projects[] | select(.project_number == '$task_number')).artifacts // [] | .[] | select(.type == "summary" | not)]' \
specs/state.json > /tmp/state.json && mv /tmp/state.json specs/state.json
# Step 5: Add new summary artifact
jq --arg path "$artifact_path" \
'(.active_projects[] | select(.project_number == '$task_number')).artifacts += [{"path": $path, "type": "summary"}]' \
specs/state.json > /tmp/state.json && mv /tmp/state.json specs/state.json
Update TODO.md:
[IMPLEMENTING] to [COMPLETED]- **Summary**: [implementation-summary-{DATE}.md]({artifact_path})Update plan file (if exists): Update the Status field to [COMPLETED] with verification:
plan_file=$(ls -1 "specs/${padded_num}_${project_name}/plans/implementation-"*.md 2>/dev/null | sort -V | tail -1)
if [ -n "$plan_file" ] && [ -f "$plan_file" ]; then
# Try bullet pattern first, then non-bullet pattern
sed -i 's/^\- \*\*Status\*\*: \[.*\]$/- **Status**: [COMPLETED]/' "$plan_file"
sed -i 's/^\*\*Status\*\*: \[.*\]$/**Status**: [COMPLETED]/' "$plan_file"
# Verify update
if grep -qE '^\*\*Status\*\*: \[COMPLETED\]|^\- \*\*Status\*\*: \[COMPLETED\]' "$plan_file"; then
echo "Plan file status updated to [COMPLETED]"
else
echo "WARNING: Could not verify plan file status update"
fi
else
echo "INFO: No plan file found to update (directory: specs/${padded_num}_${project_name}/plans/)"
fi
If result.status == "partial":
Update state.json with resume point (keep status as "implementing"):
jq --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" \
--arg phase "$completed_phase" \
'(.active_projects[] | select(.project_number == '$task_number')) |= . + {
last_updated: $ts,
resume_phase: ($phase | tonumber + 1)
}' specs/state.json > /tmp/state.json && mv /tmp/state.json specs/state.json
TODO.md stays as [IMPLEMENTING].
Update plan file (if exists): Update the Status field to [PARTIAL] with verification:
plan_file=$(ls -1 "specs/${padded_num}_${project_name}/plans/implementation-"*.md 2>/dev/null | sort -V | tail -1)
if [ -n "$plan_file" ] && [ -f "$plan_file" ]; then
# Try bullet pattern first, then non-bullet pattern
sed -i 's/^\- \*\*Status\*\*: \[.*\]$/- **Status**: [PARTIAL]/' "$plan_file"
sed -i 's/^\*\*Status\*\*: \[.*\]$/**Status**: [PARTIAL]/' "$plan_file"
# Verify update
if grep -qE '^\*\*Status\*\*: \[PARTIAL\]|^\- \*\*Status\*\*: \[PARTIAL\]' "$plan_file"; then
echo "Plan file status updated to [PARTIAL]"
else
echo "WARNING: Could not verify plan file status update"
fi
else
echo "INFO: No plan file found to update (directory: specs/${padded_num}_${project_name}/plans/)"
fi
On failed: Do NOT run postflight. Keep status as "implementing" for retry. Do not update plan file (leave as [IMPLEMENTING] for retry).
Commit changes with session ID:
git add -A
git commit -m "task ${task_number}: complete implementation
Session: ${session_id}
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>"
Remove marker and metadata files after postflight processing:
rm -f "specs/${padded_num}_${project_name}/.postflight-pending"
rm -f "specs/${padded_num}_${project_name}/.postflight-loop-guard"
rm -f "specs/${padded_num}_${project_name}/.return-meta.json"
Return a brief text summary (NOT JSON) describing the implementation results.
This skill returns a brief text summary (NOT JSON). The JSON metadata is written to the file and processed internally.
Example successful return:
LaTeX implementation completed for task 334:
- All 4 phases executed, document compiles cleanly
- Created 42-page PDF at docs/logos-manual.pdf
- Created summary at specs/334_logos_docs/summaries/implementation-summary-20260118.md
- Status updated to [COMPLETED]
- Changes committed with session sess_1736700000_abc123
Example partial return:
LaTeX implementation partially completed for task 334:
- Phases 1-2 of 3 executed
- Phase 3 blocked: missing tikz-cd package
- Partial summary at specs/334_logos_docs/summaries/implementation-summary-20260118.md
- Status remains [IMPLEMENTING] - run /implement 334 to resume
Return immediately with failed status if task not found, wrong language, or status invalid.
Pass through the subagent's error return verbatim.
Return partial status if subagent times out (default 3600s).