fecfile

Name: fecfile
Author: hodgesmr

38stars5forks

How to install fecfile?

hodgesmr/agent-fecfile/fecfile

$npx -y skills add hodgesmr/agent-fecfile --skill fecfile

Installs into the current project.

Summary

Analyze FEC (Federal Election Commission) campaign finance filings. Use when working with FEC filing IDs, campaign finance data, contributions, disbursements, or political committee financial reports. Provides the proper workflow for the fec-api MCP tools (search_committees, get_

Files · 1

View on GitHub

SKILL.md

1	# FEC Filing Analysis
2
3	This skill enables analysis of Federal Election Commission campaign finance filings.
4
5	## Requirements
6
7	- [uv](https://docs.astral.sh/uv/) must be installed
8	- Python 3.9+
9
10	Dependencies are automatically installed when running scripts with `uv run`.
11
12	## First-Time Check
13
14	The first time this skill is invoked in a session, verify that `uv` is installed by running:
15
16	```bash
17	uv --version
18	```
19
20	If this command fails or `uv` is not found, do not proceed. Instead, inform the user that `uv` is required but not installed, and direct them to the installation guide: https://docs.astral.sh/uv/getting-started/installation/
21
22	## Quick Start
23
24	Always start by checking the filing size:
25	```bash
26	uv run scripts/fetch_filing.py <FILING_ID> --summary-only
27	```
28
29	Based on the summary, decide how to proceed—see Handling Large Filings below for filtering and streaming strategies. Small filings can be fetched directly; large filings require pre-filtering or streaming.
30
31	Fetching data:
32	```bash
33	uv run scripts/fetch_filing.py <FILING_ID> # Full filing (small filings only)
34	uv run scripts/fetch_filing.py <FILING_ID> --schedule A # Only contributions
35	uv run scripts/fetch_filing.py <FILING_ID> --schedule B # Only disbursements
36	uv run scripts/fetch_filing.py <FILING_ID> --schedules A,B # Multiple schedules
37	```
38
39	The `fecfile` library is installed automatically by uv.
40
41	## Field Name Policy
42
43	IMPORTANT: Do not guess at field names. Before referencing any field names in responses:
44
45	1. For form-level fields (summary data, cash flow, totals): Read `references/FORMS.md`
46	2. For itemization fields (contributors, payees, expenditures): Read `references/SCHEDULES.md`
47
48	These files contain the authoritative field mappings. If a field name isn't documented there, verify it exists in the actual JSON output before using it.
49
50	## Handling Large Filings
51
52	FEC filings vary enormously in size. Small filings (like state party monthly reports) may have only a few dozen itemizations and can be used directly. However, major committees like ActBlue, WinRed, and presidential campaigns can have hundreds of thousands of itemizations in a single filing. Do not dump large filing data directly into the context window. Avoid streaming large filings to stdout.
53
54	### Checking Size
55
56	Before pulling full schedules, use `--summary-only` to assess the filing:
57
58	```bash
59	uv run scripts/fetch_filing.py <ID> --summary-only
60	```
61
62	The summary includes financial totals that help gauge filing size without parsing itemizations:
63
64	\| Field \| Description \|
65	\|-------\|-------------\|
66	\| `col_a_individuals_itemized` \| Itemized individual contributions (this period) \|
67	\| `col_a_total_contributions` \| Total contributions (this period) \|
68	\| `col_a_total_disbursements` \| Total disbursements (this period) \|
69	\| `col_b_individuals_itemized` \| Itemized individual contributions (year-to-date) \|
70	\| `col_b_total_contributions` \| Total contributions (year-to-date) \|
71	\| `col_b_total_disbursements` \| Total disbursements (year-to-date) \|
72
73	These are dollar totals, not item counts, but combined with the committee name they help you decide:
74	- Small state/local party with modest totals: Probably safe to pull full schedules
75	- ActBlue, WinRed, or presidential campaign with millions in totals: Use streaming or post-filter
76
77	If you need to verify exact counts before processing, stream with an early cutoff:
78
79	```bash
80	uv run scripts/fetch_filing.py <ID> --stream --schedule A \| python3 -c "
81	import sys
82	count = 0
83	limit = 256
84	for line in sys.stdin:
85	count += 1
86	if count >= limit:
87	print(f'Schedule A: {limit}+ items (stopped counting)')
88	sys.exit(0)
89	print(f'Schedule A: {count} items')
90	"
91	```
92
93	If itemization counts are in the hundreds or more, you must post-filter before presenting results. Even smaller filings may benefit from post-filtering to aggregate or focus the output.
94
95	### Pre-Filtering at Parse Time
96
97	Use CLI flags to filter before data is loaded into memory:
98
99	\| Flag \| Effect \|
100	\|------\|--------\|
101	\| `--summary-only` \| Only filing summary (no itemizations) \|
102	\| `--schedule A` \| Only Schedule A (contributions) \|
103	\| `--schedule B` \| Only Schedule B (disbursements) \|
104	\| `--schedule C` \| Only Schedule C (loans) \|
105	\| `--schedule D` \| Only Schedule D (debts) \|
106	\| `--schedule E` \| Only Schedule E (independent expenditures) \|
107	\| `--schedules A,B` \| Multiple schedules (comma-separated) \|
108
109	Schedules you don't request are never parsed.
110
111	### Post-Filtering with Pandas
112
113	Use Python/pandas to aggregate, filter, and limit results:

People who liked this also viewed

6 picks

Type

fecfile

38stars5forks

View on GitHub

How to install fecfile?

hodgesmr/agent-fecfile/fecfile

$npx -y skills add hodgesmr/agent-fecfile --skill fecfile

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# FEC Filing Analysis
2
3	This skill enables analysis of Federal Election Commission campaign finance filings.
4
5	## Requirements
6
7	- [uv](https://docs.astral.sh/uv/) must be installed
8	- Python 3.9+
9
10	Dependencies are automatically installed when running scripts with `uv run`.
11
12	## First-Time Check
13
14	The first time this skill is invoked in a session, verify that `uv` is installed by running:
15
16	```bash
17	uv --version
18	```
19
20	If this command fails or `uv` is not found, do not proceed. Instead, inform the user that `uv` is required but not installed, and direct them to the installation guide: https://docs.astral.sh/uv/getting-started/installation/
21
22	## Quick Start
23
24	Always start by checking the filing size:
25	```bash
26	uv run scripts/fetch_filing.py <FILING_ID> --summary-only
27	```
28
29	Based on the summary, decide how to proceed—see Handling Large Filings below for filtering and streaming strategies. Small filings can be fetched directly; large filings require pre-filtering or streaming.
30
31	Fetching data:
32	```bash
33	uv run scripts/fetch_filing.py <FILING_ID> # Full filing (small filings only)
34	uv run scripts/fetch_filing.py <FILING_ID> --schedule A # Only contributions
35	uv run scripts/fetch_filing.py <FILING_ID> --schedule B # Only disbursements
36	uv run scripts/fetch_filing.py <FILING_ID> --schedules A,B # Multiple schedules
37	```
38
39	The `fecfile` library is installed automatically by uv.
40
41	## Field Name Policy
42
43	IMPORTANT: Do not guess at field names. Before referencing any field names in responses:
44
45	1. For form-level fields (summary data, cash flow, totals): Read `references/FORMS.md`
46	2. For itemization fields (contributors, payees, expenditures): Read `references/SCHEDULES.md`
47
48	These files contain the authoritative field mappings. If a field name isn't documented there, verify it exists in the actual JSON output before using it.
49
50	## Handling Large Filings
51
52	FEC filings vary enormously in size. Small filings (like state party monthly reports) may have only a few dozen itemizations and can be used directly. However, major committees like ActBlue, WinRed, and presidential campaigns can have hundreds of thousands of itemizations in a single filing. Do not dump large filing data directly into the context window. Avoid streaming large filings to stdout.
53
54	### Checking Size
55
56	Before pulling full schedules, use `--summary-only` to assess the filing:
57
58	```bash
59	uv run scripts/fetch_filing.py <ID> --summary-only
60	```
61
62	The summary includes financial totals that help gauge filing size without parsing itemizations:
63
64	\| Field \| Description \|
65	\|-------\|-------------\|
66	\| `col_a_individuals_itemized` \| Itemized individual contributions (this period) \|
67	\| `col_a_total_contributions` \| Total contributions (this period) \|
68	\| `col_a_total_disbursements` \| Total disbursements (this period) \|
69	\| `col_b_individuals_itemized` \| Itemized individual contributions (year-to-date) \|
70	\| `col_b_total_contributions` \| Total contributions (year-to-date) \|
71	\| `col_b_total_disbursements` \| Total disbursements (year-to-date) \|
72
73	These are dollar totals, not item counts, but combined with the committee name they help you decide:
74	- Small state/local party with modest totals: Probably safe to pull full schedules
75	- ActBlue, WinRed, or presidential campaign with millions in totals: Use streaming or post-filter
76
77	If you need to verify exact counts before processing, stream with an early cutoff:
78
79	```bash
80	uv run scripts/fetch_filing.py <ID> --stream --schedule A \| python3 -c "
81	import sys
82	count = 0
83	limit = 256
84	for line in sys.stdin:
85	count += 1
86	if count >= limit:
87	print(f'Schedule A: {limit}+ items (stopped counting)')
88	sys.exit(0)
89	print(f'Schedule A: {count} items')
90	"
91	```
92
93	If itemization counts are in the hundreds or more, you must post-filter before presenting results. Even smaller filings may benefit from post-filtering to aggregate or focus the output.
94
95	### Pre-Filtering at Parse Time
96
97	Use CLI flags to filter before data is loaded into memory:
98
99	\| Flag \| Effect \|
100	\|------\|--------\|
101	\| `--summary-only` \| Only filing summary (no itemizations) \|
102	\| `--schedule A` \| Only Schedule A (contributions) \|
103	\| `--schedule B` \| Only Schedule B (disbursements) \|
104	\| `--schedule C` \| Only Schedule C (loans) \|
105	\| `--schedule D` \| Only Schedule D (debts) \|
106	\| `--schedule E` \| Only Schedule E (independent expenditures) \|
107	\| `--schedules A,B` \| Multiple schedules (comma-separated) \|
108
109	Schedules you don't request are never parsed.
110
111	### Post-Filtering with Pandas
112
113	Use Python/pandas to aggregate, filter, and limit results:

People who liked this also viewed

6 picks

Type